Recommendation systems often rely on implicit feedback, where only positive user-item interactions can be observed. Negative sampling is therefore crucial to provide proper negative training signals. However, existing methods tend to mislabel potentially positive but unobserved items as negatives and lack precise control over negative sample selection. We aim to address these by generating controllable negative samples, rather than sampling from the existing item pool. In this context, we propose Adaptive Diffusion-based Augmentation for Recommendation (ADAR), a novel and model-agnostic module that leverages diffusion to synthesize informative negatives. Inspired by the progressive corruption process in diffusion, ADAR simulates a continuous transition from positive to negative, allowing for fine-grained control over sample hardness. To mine suitable negative samples, we theoretically identify the transition point at which a positive sample turns negative and derive a score-aware function to adaptively determine the optimal sampling timestep. By identifying this transition point, ADAR generates challenging negative samples that effectively refine the model's decision boundary. Experiments confirm that ADAR is broadly compatible and boosts the performance of existing recommendation models substantially, including collaborative filtering and sequential recommendation, without architectural modifications.

Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Existing methods, whether based on distribution matching or self-supervised learning, often focus solely on classifying individual source samples, potentially overlooking discriminative information. To address this limitation, we propose FlowUDA, a novel plugin method that enhances existing UDA frameworks by constructing semantically invariant flows from individual source samples to corresponding target samples, forming cross-domain trajectories. By leveraging a diffusion network guided by ordinary differential equations, FlowUDA ensures these flows preserve the topological structure of the source domain, maintaining their distinguishability. Our method then classifies these flows by sampling points along them and transferring labels from source samples, effectively capturing spatial relationships between domains. In essence, FlowUDA transforms the traditional point-based classification on individual source samples into flow-based classification on flows, allowing the model to learn richer, more discriminative features that bridge the gap between source and target domains. Extensive experiments on standard benchmarks demonstrate that integrating FlowUDA into existing UDA methods leads to notable performance gains, highlighting its effectiveness in addressing domain shift challenges.

Audio-Visual Segmentation (AVS) aims to identify, at the pixel level, the object in a visual scene that produces a given sound. Current AVS methods rely on costly fine-grained annotations of mask-audio pairs, making them impractical for scalability. To address this, we propose the Modality Correspondence Alignment (MoCA) framework, which seamlessly integrates off-the-shelf foundation models like DINO, SAM, and ImageBind. Our approach leverages existing knowledge within these models and optimizes their joint usage for multimodal associations. Our approach relies on estimating positive and negative image pairs in the feature space. For pixel-level association, we introduce an audio-visual adapter and a novel {pixel matching aggregation} strategy within the image-level contrastive learning framework. This allows for a flexible connection between object appearance and audio signal at the pixel level, with tolerance to imaging variations such as translation and rotation. Extensive experiments on the AVSBench (single and multi-object splits) and AVSS datasets demonstrate that MoCA outperforms unsupervised baseline approaches and some supervised counterparts, particularly in complex scenarios with multiple auditory objects. In terms of mIoU, MoCA achieves a substantial improvement over baselines in both the AVSBench (S4: +17.24%, MS3: +67.64%) and AVSS (+19.23%) audio-visual segmentation challenges.

Unmanned Aerial Vehicle Object Detection (UAVOD) presents unique challenges due to varying altitudes, dynamic backgrounds, and the small size of objects. Traditional detection methods often struggle with these challenges, as they typically rely on visual feature only and fail to extract the semantic relations between the objects. To address these limitations, we propose a novel approach named Self-Prompting Analogical Reasoning (SPAR). Our method utilizes the vision-language model (CLIP) to generate context-aware prompts based on image feature, providing rich semantic information that guides analogical reasoning. SPAR includes two main modules: self-prompting and analogical reasoning. Self-prompting module based on learnable description and CLIP-text encoder generates context-aware prompt by combining specific image feature; then an objectness prompt score map is produced by computing the similarity between pixel-level features and context-aware prompt. With this score map, multi-scale image features are enhanced and pixel-level features are chosen for graph construction. While for analogical reasoning module, graph nodes consists of category-level prompt nodes and pixel-level image feature nodes. Analogical inference is based graph convolution. Under the guidance of category-level nodes, different-scale object features have been enhanced, which helps achieve more accurate detection of challenging objects. Extensive experiments illustrate that SPAR outperforms traditional methods, offering a more robust and accurate solution for UAVOD.

Object counting is pivotal for understanding the composition of scenes. Previously, this task was dominated by class-specific methods, which have gradually evolved into more adaptable class-agnostic strategies. However, these strategies come with their own set of limitations, such as the need for manual exemplar input and multiple passes for multiple categories, resulting in significant inefficiencies. This paper introduces a more practical approach enabling simultaneous counting of multiple object categories using an open-vocabulary framework. Our solution, OmniCount, stands out by using semantic and geometric insights (priors) from pre-trained models to count multiple categories of objects as specified by users, all without additional training. OmniCount distinguishes itself by generating precise object masks and leveraging varied interactive prompts via the Segment Anything Model for efficient counting. To evaluate OmniCount, we created the OmniCount-191 benchmark, a first-of-its-kind dataset with multi-label object counts, including points, bounding boxes, and VQA annotations. Our comprehensive evaluation in OmniCount-191, alongside other leading benchmarks, demonstrates OmniCount's exceptional performance, significantly outpacing existing solutions.

Point management is critical for optimizing 3D Gaussian Splatting models, as point initiation (e.g., via structure from motion) is often distributionally inappropriate. Typically, Adaptive Density Control (ADC) algorithm is adopted, leveraging view-averaged gradient magnitude thresholding for point densification, opacity thresholding for pruning, and regular all-points opacity reset. We reveal that this strategy is limited in tackling intricate/special image regions (e.g., transparent) due to inability of identifying all 3D zones requiring point densification, and lacking an appropriate mechanism to handle ill-conditioned points with negative impacts (e.g., occlusion due to false high opacity). To address these limitations, we propose a Localized Point Management (LPM) strategy, capable of identifying those error-contributing zones in greatest need for both point addition and geometry calibration. Zone identification is achieved by leveraging the underlying multiview geometry constraints, subject to image rendering errors. We apply point densification in the identified zones and then reset the opacity of the points in front of these regions, creating a new opportunity to correct poorly conditioned points. Serving as a versatile plugin, LPM can be seamlessly integrated into existing static 3D and dynamic 4D Gaussian Splatting models with minimal additional cost. Experimental evaluations validate the efficacy of our LPM in boosting a variety of existing 3D/4D models both quantitatively and qualitatively. Notably, LPM improves both static 3DGS and dynamic SpaceTimeGS to achieve state-of-the-art rendering quality while retaining real-time speeds, excelling on challenging datasets such as Tanks & Temples and the Neural 3D Video dataset.

Diffusion models are proficient at generating high-quality images. They are however effective only when operating at the resolution used during training. Inference at a scaled resolution leads to repetitive patterns and structural distortions. Retraining at higher resolutions quickly becomes prohibitive. Thus, methods enabling pre-existing diffusion models to operate at flexible test-time resolutions are highly desirable. Previous works suffer from frequent artifacts and often introduce large latency overheads. We propose two simple modules that combine to solve these issues. We introduce a Frequency Modulation (FM) module that leverages the Fourier domain to improve the global structure consistency, and an Attention Modulation (AM) module which improves the consistency of local texture patterns, a problem largely ignored in prior works. Our method, coined FAM diffusion, can seamlessly integrate into any latent diffusion model and requires no additional training. Extensive qualitative results highlight the effectiveness of our method in addressing structural and local artifacts, while quantitative results show state-of-the-art performance. Also, our method avoids redundant inference tricks for improved consistency such as patch-based or progressive generation, leading to negligible latency overheads. FAM diffusion project webpage: https://happy-hsy.github.io/projects/Famdiffusion/

Inverse rendering aims to recover scene geometry, material properties, and lighting from multi-view images. Given the complexity of light-surface interactions, importance sampling is essential for the evaluation of the rendering equation, as it reduces variance and enhances the efficiency of Monte Carlo sampling. Existing inverse rendering methods typically use pre-defined non-learnable importance samplers in prior manually, struggling to effectively match the spatially and directionally varied integrand and resulting in high variance and suboptimal performance. To address this limitation, we propose the concept of learning a spatially and directionally aware importance sampler for the rendering equation to accurately and flexibly capture the unconstrained complexity of a typical scene. We further formulate TensoFlow, a generic approach for sampler learning in inverse rendering, enabling to closely match the integrand of the rendering equation spatially and directionally. Concretely, our sampler is parameterized by normalizing flows, allowing both directional sampling of incident light and probability density function (PDF) inference. To capture the characteristics of the sampler spatially, we learn a tensorial representation of the scene space, which imposes spatial conditions, together with reflected direction, leading to spatially and directionally aware sampling distributions. Our model can be optimized by minimizing the difference between the integrand and our normalizing flow. Extensive experiments validate the superiority of TensoFlow over prior alternatives on both synthetic and real-world benchmarks.

Domain shift (the difference between source and target domains) poses a significant challenge in clinical applications, e.g., Diabetic Retinopathy (DR) grading. Despite considering certain clinical requirements, like source data privacy, conventional transfer methods are predominantly model-centered and often struggle to prevent model-targeted attacks. In this paper, we address a challenging Online Model-aGnostic Domain Adaptation (OMG-DA) setting, driven by the demands of clinical environments. This setting is characterized by the absence of the model and the flow of target data. To tackle the new challenge, we propose a novel approach, Generative Unadversarial ExampleS (GUES), which enables adaptation from a data-centric perspective. Specifically, we first theoretically reformulate conventional perturbation optimization in a generative way—learning a perturbation generation function with a latent input variable. During model instantiation, we leverage a Variational AutoEncoder to express this function. The encoder with the reparameterization trick predicts the latent input, whilst the decoder is responsible for the generation. Furthermore, the saliency map is selected as pseudo-perturbation labels. Because it not only captures potential lesions but also theoretically provides an upper bound on the function input, enabling the identification of the latent variable. Extensive experiments on DR benchmarks with both frozen pre-trained models and trainable models demonstrate the superiority of GUES, showing robustness even with small batch size. The source code and data are available at https://github.com/tntek/GUES.

Test-time adaptation with pre-trained vision-language models, such as CLIP, aims to adapt the model to new, potentially out-of-distribution test data. Existing methods calculate the similarity between visual embedding and learnable class embeddings, which are initialized by text embeddings, for zero-shot image classification. In this work, we first analyze this process based on Bayes theorem, and observe that the core factors influencing the final prediction are the likelihood and the prior. However, existing methods essentially focus on adapting class embeddings to adapt likelihood, but they often ignore the importance of prior. To address this gap, we propose a novel approach, Bayesian Class Adaptation (BCA), which in addition to continuously updating class embeddings to adapt likelihood, also uses the posterior of incoming samples to continuously update the prior for each class embedding. This dual updating mechanism allows the model to better adapt to distribution shifts and achieve higher prediction accuracy. Our method not only surpasses existing approaches in terms of performance metrics but also maintains superior inference rates and memory usage, making it highly efficient and practical for real-world applications.

As critical visual details become obscured, the low visibility and high ISO noise in extremely low-light images pose a significant challenge to human pose estimation. Current methods fail to provide high-quality representations due to reliance on pixel-level enhancements that compromise semantics and the inability to effectively handle extreme low-light conditions for robust feature learning. In this work, we propose a frequency-based framework for low-light human pose estimation, rooted in the "divide-and-conquer" principle. Instead of uniformly enhancing the entire image, our method focuses on task-relevant information. By applying dynamic illumination correction to the low-frequency components and low-rank denoising to the high-frequency components, we effectively enhance both the semantic and texture information essential for accurate pose estimation. As a result, this targeted enhancement method results in robust, high-quality representations, significantly improving pose estimation performance. Extensive experiments demonstrating its superiority over state-of-the-art methods in various challenging low-light scenarios.

Pose distillation is widely adopted to reduce model size in human pose estimation. However, existing methods primarily emphasize the transfer of teacher knowledge while often neglecting the performance degradation resulted from the curse of capacity gap between teacher and student. To address this issue, we propose AgentPose, a novel pose distillation method that integrates a feature agent to model the distribution of teacher features and progressively aligns the distribution of student features with that of the teacher feature, effectively overcoming the capacity gap and enhancing the ability of knowledge transfer. Our comprehensive experiments conducted on the COCO dataset substantiate the effectiveness of our method in knowledge transfer, particularly in scenarios with a high capacity gap.

Synthesizing normal-light novel views from low-light multiview images is an important yet challenging task, given the low visibility and high ISO noise present in the input images. Existing low-light enhancement methods often struggle to effectively preprocess such low-light inputs, as they fail to consider correlations among multiple views. Although other state-of-the-art methods have introduced illumination-related components offering alternative solutions to the problem, they often result in drawbacks such as color distortions and artifacts, and they provide limited denoising effectiveness. In this paper, we propose a novel Robust Low-light Scene Restoration framework (RoSe), which enables effective synthesis of novel views in normal lighting conditions from low-light multiview image inputs, by formulating the task as an illuminance transition estimation problem in 3D space, conceptualizing it as a specialized rendering task. This multiview-consistent illuminance transition field establishes a robust connection between low-light and normal-light conditions. By further exploiting the inherent low-rank property of illumination to constrain the transition representation, we achieve more effective denoising without complex 2D techniques or explicit noise modeling. To implement RoSe, we design a concise dual-branch architecture and introduce a low-rank denoising module. Experiments demonstrate that RoSe significantly outperforms state-of-the-art models in both rendering quality and multiview consistency on standard benchmarks. The codes and data are available at https://pegasus2004.github.io/RoSe.

Source-Free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to an unlabeled target domain with no access to the source data. Inspired by the success of large Vision-Language (ViL) models in many applications, the latest research has validated ViL's benefit for SFDA by using their predictions as pseudo supervision. However, we observe that ViL's supervision could be noisy and inaccurate at an unknown rate, potentially introducing additional negative effects during adaption. To address this thus-far ignored challenge, we introduce a novel Proxy Denoising (__ProDe__) approach. The key idea is to leverage the ViL model as a proxy to facilitate the adaptation process towards the latent domain-invariant space. Concretely, we design a proxy denoising mechanism to correct ViL's predictions. This is grounded on a proxy confidence theory that models the dynamic effect of proxy's divergence against the domain-invariant space during adaptation. To capitalize the corrected proxy, we further derive a mutual knowledge distilling regularization. Extensive experiments show that ProDe significantly outperforms the current state-of-the-art alternatives under both conventional closed-set setting and the more challenging open-set, partial-set, generalized SFDA, multi-target, multi-source, and test-time settings. Our code and data are available at https://github.com/tntek/source-free-domain-adaptation.

Ranking samples by fine-grained estimates of spuriosity (the degree to which spurious cues are present) has recently been shown to significantly benefit bias mitigation, over the traditional binary biased-vs-unbiased partitioning of train sets. However, this spuriousity ranking comes with the requirement of human supervision. In this paper, we propose a debiasing framework based on our novel Self-Guided Bias Ranking (Sebra), that mitigates biases via an automatic ranking of data points by spuriosity within their respective classes. Sebra leverages a key local symmetry in Empirical Risk Minimization (ERM) training -- the ease of learning a sample via ERM inversely correlates with its spuriousity; the fewer spurious correlations a sample exhibits, the harder it is to learn, and vice versa. However, globally across iterations, ERM tends to deviate from this symmetry. Sebra dynamically steers ERM to correct this deviation, facilitating the sequential learning of attributes in increasing order of difficulty, ie, decreasing order of spuriosity. As a result, the sequence in which Sebra learns samples naturally provides spuriousity rankings. We use the resulting fine-grained bias characterization in a contrastive learning framework to mitigate biases from multiple sources. Extensive experiments show that Sebra consistently outperforms previous state-of-the-art unsupervised debiasing techniques across multiple standard benchmarks, including UrbanCars, BAR, and CelebA.

Novel view synthesis has experienced significant advancements owing to increasingly capable NeRF- and 3DGS-based methods. However, reflective object reconstruction remains challenging, lacking a proper solution to achieve real-time, high-quality rendering while accommodating inter-reflection. To fill this gap, we introduce a Reflective Gaussian splatting (Ref-Gaussian) framework characterized with two components: (I) Physically based deferred rendering that empowers the rendering equation with pixel-level material properties via formulating split-sum approximation; (II) Gaussian-grounded inter-reflection that realizes the desired inter-reflection function within a Gaussian splatting paradigm for the first time. To enhance geometry modeling, we further introduce material-aware normal propagation and an initial per-Gaussian shading stage, along with 2D Gaussian primitives. Extensive experiments on standard datasets demonstrate that Ref-Gaussian surpasses existing approaches in terms of quantitative metrics, visual quality, and compute efficiency. Further, we show that our method serves as a unified solution for both reflective and non-reflective scenes, going beyond the previous alternatives focusing on only reflective scenes. Also, we illustrate that Ref-Gaussian supports more applications such as relighting and editing.

Unsupervised anomaly detection (UAD) seeks to localize the anomaly mask of an input image with respect to normal samples. Either by reconstructing normal counterparts (reconstruction-based) or by learning an image feature embedding space (embedding-based), existing approaches fundamentally rely on image-level or feature-level matching to derive anomaly scores. Often, such a matching process is inaccurate yet overlooked, leading to sub-optimal detection. To address this issue, we introduce the concept of cost filtering, borrowed from classical matching tasks, such as depth and flow estimation, into the UAD problem. We call this approach CostFilter-AD. Specifically, we first construct a matching cost volume between the input and normal samples, comprising two spatial dimensions and one matching dimension that encodes potential matches. To refine this, we propose a cost volume filtering network, guided by the input observation as an attention query across multiple feature layers, which effectively suppresses matching noise while preserving edge structures and capturing subtle anomalies. Designed as a generic post-processing plug-in, CostFilter-AD can be integrated with either reconstruction-based or embedding-based methods. Extensive experiments on MVTec-AD and VisA benchmarks validate the generic benefits of CostFilter-AD for both single- and multi-class UAD tasks. Code and models will be released at https://github.com/ZHE-SAPI/CostFilter-AD.

High Dynamic Range Novel View Synthesis (HDR-NVS) aims to establish a 3D scene HDR model from Low Dynamic Range (LDR) imagery. Typically, multiple-exposure LDR images are employed to capture a wider range of brightness levels in a scene, as a single LDR image cannot represent both the brightest and darkest regions simultaneously. While effective, this multiple-exposure HDR-NVS approach has significant limitations, including susceptibility to motion artifacts (e.g., ghosting and blurring), high capture and storage costs. To overcome these challenges, we introduce, for the first time, the single-exposure HDR-NVS problem, where only single exposure LDR images are available during training. We further introduce a novel approach, Mono-HDR-3D, featuring two dedicated modules formulated by the LDR image formation principles, one for converting LDR colors to HDR counterparts, and the other for transforming HDR images to LDR format so that unsupervised learning is enabled in a closed loop. Designed as a meta-algorithm, our approach can be seamlessly integrated with existing NVS models. Extensive experiments show that Mono-HDR-3D significantly outperforms previous methods. Source code is released at https://github.com/prinasi/Mono-HDR-3D.

Motion simulation, prediction and planning are foundational tasks in autonomous driving, each essential for modeling and reasoning about dynamic traffic scenarios. While often addressed in isolation due to their differing objectives, such as generating diverse motion states or estimating optimal trajectories, these tasks inherently depend on shared capabilities: understanding multi-agent interactions, modeling motion behaviors, and reasoning over temporal and spatial dynamics. Despite this underlying commonality, existing approaches typically adopt specialized model designs, which hinders cross-task generalization and system scalability. More critically, this separation overlooks the potential mutual benefits among tasks. Motivated by these observations, we propose **UniMotion**, a unified motion framework that captures shared structures across motion tasks while accommodating their individual requirements. Built on a decoder-only Transformer architecture, UniMotion employs dedicated interaction modes and tailored training strategies to simultaneously support these motion tasks. This unified design not only enables joint optimization and representation sharing but also allows for targeted fine-tuning to specialize in individual tasks when needed. Extensive experiments on the Waymo Open Motion Dataset (WOMD) demonstrate that joint training leads to robust generalization and effective task integration. With further fine-tuning, UniMotion achieves state-of-the-art performance across a range of motion tasks, establishing it as a versatile and scalable solution for autonomous driving.

This paper introduces **VimoRAG**, a novel video-based retrieval-augmented motion generation framework for motion large language models (LLMs). As motion LLMs face severe out-of-domain/out-of-vocabulary issues due to limited annotated data, **VimoRAG** leverages large-scale in-the-wild video databases to enhance 3D motion generation by retrieving relevant 2D human motion signals. While video-based motion RAG is nontrivial, we address two key bottlenecks: (1) developing an effective motion-centered video retrieval model that distinguishes human poses and actions, and (2) mitigating the issue of error propagation caused by suboptimal retrieval results. We design the Gemini Motion Video Retriever mechanism and the Motion-centric Dual-alignment DPO Trainer, enabling effective retrieval and generation processes. Experimental results show that **VimoRAG** significantly boosts the performance of motion LLMs constrained to text-only input.

End-to-end autonomous driving methods aim to directly map raw sensor inputs to future driving actions such as planned trajectories, bypassing traditional modular pipelines. While these approaches have shown promise, they often operate under a one-shot paradigm that relies heavily on the current scene context, potentially underestimating the importance of scene dynamics and their temporal evolution. This limitation restricts the model’s ability to make informed and adaptive decisions in complex driving scenarios. We propose a new perspective: the future trajectory of an autonomous vehicle is closely intertwined with the evolving dynamics of its environment, and conversely, the vehicle’s own future states can influence how the surrounding scene unfolds. Motivated by this bidirectional relationship, we introduce **SeerDrive**, a novel end-to-end framework that jointly models future scene evolution and trajectory planning in a closed-loop manner. Our method first predicts future bird’s-eye view (BEV) representations to anticipate the dynamics of the surrounding scene, then leverages this foresight to generate future-context-aware trajectories. Two key components enable this: (1) future-aware planning, which injects predicted BEV features into the trajectory planner, and (2) iterative scene modeling and vehicle planning, which refines both future scene prediction and trajectory generation through collaborative optimization. Extensive experiments on the NAVSIM and nuScenes benchmarks show that SeerDrive significantly outperforms existing state-of-the-art methods.

DDoS (Distributed Denial of Service) attacks are increasingly becoming a major threat in the field of cybersecurity. They overwhelm target servers by sending large-scale requests from multiple locations, causing the servers to become unresponsive. The distributed nature of DDoS attacks also makes detection and defense even more challenging. As the damage caused by such attacks grows, the development of efficient detection and mitigation mechanisms has become an urgent priority. While traditional machine learning methods are useful, they still require manual feature extraction, which not only involves significant human intervention, but also is time-consuming. In contrast, deep learning offers an automated approach to feature extraction and can learn more abstract patterns, which leads to improved detection performance. Therefore, this paper reviews and analyzes existing deep learning methods for DDoS attack detection. We provide a comprehensive analysis of the various types of DDoS attacks and explore different deep learning models employed for attack detection. Additionally, we explore techniques such as federated learning that can be integrated with deep learning, and analyze their related literature in DDoS attack detection. Finally, we specify future research directions on DDoS attack detection using deep learning.

Abstract Existing knowledge distillation methods mostly focus on distillation of teacher’s prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is largely overlooked. In this work, we propose a novel semantic representational distillation (SRD) method dedicated for distilling representational knowledge semantically from a pretrained teacher to a target student. The key idea is that we leverage the teacher’s classifier as a semantic critic for evaluating the representations of both teacher and student and distilling the semantic knowledge with high-order structured information over all feature dimensions. This is accomplished by introducing a notion of cross-network logit computed through passing student’s representation into teacher’s classifier. Further, considering the set of seen classes as a basis for the semantic space in a combinatorial perspective, we scale SRD to unseen classes for enabling effective exploitation of largely available, arbitrary unlabeled training data. At the problem level, this establishes an interesting connection between knowledge distillation with open-set semi-supervised learning (SSL). Extensive experiments show that our SRD outperforms significantly previous state-of-the-art knowledge distillation methods on both coarse object classification and fine face recognition tasks, as well as less studied yet practically crucial binary network distillation. Under more realistic open-set SSL settings we introduce, we reveal that knowledge distillation is generally more effective than existing out-of-distribution sample detection, and our proposed SRD is superior over both previous distillation and SSL competitors. The source code is available at https://github.com/jingyang2017/SRD_ossl .

Few-shot Semantic Segmentation (FSS) aims to adapt a pretrained model to new classes with as few as a single labeled training sample per class. Despite the prototype based approaches have achieved substantial success, existing models are limited to the imaging scenarios with considerably distinct objects and not highly complex background, e.g., natural images. This makes such models suboptimal for medical imaging with both conditions invalid. To address this problem, we propose a novel D etail S elf-refined P rototype Net work ( DSPNet ) to construct high-fidelity prototypes representing the object foreground and the background more comprehensively. Specifically, to construct global semantics while maintaining the captured detail semantics, we learn the foreground prototypes by modeling the multimodal structures with clustering and then fusing each in a channel-wise manner. Considering that the background often has no apparent semantic relation in the spatial dimensions, we integrate channel-specific structural information under sparse channel-aware regulation. Extensive experiments on three challenging medical image benchmarks show the superiority of DSPNet over previous state-of-the-art methods. The code and data are available at https://github.com/tntek/DSPNet . • A novel prototypical FSS approach DSPNet that enhances prototypes’ self-representation. • A class prototype self-refining method FSPA integrating the cluster prototypes. • A background prototype self-refining method BCMA coding channel-specific structure.

Existing top-performance autonomous driving systems typically rely on the multi-modal fusion strategy for reliable scene understanding. This design is however fundamentally restricted due to overlooking the modality-specific strengths and finally hampering the model performance. To address this limitation, in this work, we introduce a novel modality interaction strategy that allows individual per-modality representations to be learned and maintained throughout, enabling their unique characteristics to be exploited during the whole perception pipeline. To demonstrate the effectiveness of the proposed strategy, we design DeepInteraction++, a multi-modal interaction framework characterized by a multi-modal representational interaction encoder and a multi-modal predictive interaction decoder. Specifically, the encoder is implemented as a dual-stream Transformer with specialized attention operation for information exchange and integration between separate modality-specific representations. Our multi-modal representational learning incorporates both object-centric, precise sampling-based feature alignment and global dense information spreading, essential for the more challenging planning task. The decoder is designed to iteratively refine the predictions by alternately aggregating information from separate representations in a unified modality-agnostic manner, realizing multi-modal predictive interaction. Extensive experiments demonstrate the superior performance of the proposed framework on both 3D object detection and end-to-end autonomous driving tasks.

Unsupervised Domain Adaptive Semantic Segmentation (UDA-SS) aims to transfer the supervision from a labeled source domain to an unlabeled and shifted target domain. The majority of existing UDA-SS works typically consider images whilst recent attempts have extended further to tackle videos by modeling the temporal dimension. Although two lines of research share the major challenges - overcoming the underlying domain distribution shift, their studies are largely independent. It causes several issues: (1) The insights gained from each line of research remain fragmented, leading to a lack of holistic understanding of the problem and potential solutions. (2) Preventing the unification of methods and best practices across two scenarios (images and videos) will lead to redundant efforts and missed opportunities for cross-pollination of ideas. (3) Without a unified approach, the knowledge and advancements made in one scenario may not be effectively transferred to the other, leading to suboptimal performance and slower progress. Under this observation, we advocate unifying the study of UDA-SS across video and image scenarios, enabling a more comprehensive understanding, synergistic advancements, and efficient knowledge sharing. To that end, we explore the unified UDA-SS from a general domain augmentation perspective, serving as a unifying framework, enabling improved generalization, and potential for cross-pollination, ultimately contributing to the practical impact and overall progress. Specifically, we propose a Quad-directional Mixup (QuadMix) method, characterized by tackling intra-domain discontinuity, fragmented gap bridging, and feature inconsistencies through four-directional paths designed for intra- and inter-domain mixing within an explicit feature space. To deal with temporal shifts within videos, we incorporate optical flow-guided feature aggregation across spatial and temporal dimensions for fine-grained domain alignment, which is extendable to image scenarios. Extensive experiments show that QuadMix outperforms the state-of-the-art works by large margins on four challenging UDA-SS benchmarks.

Sound Event Detection (SED) aims to predict the temporal boundaries of all the events of interest and their class labels, given an unconstrained audio sample. Taking either the split-and-classify (i.e., frame-level) strategy or the more principled event-level modeling approach, all existing methods consider the SED problem from the discriminative learning perspective. In this work, we reformulate the SED problem by taking a generative learning perspective. Specifically, we aim to generate sound temporal boundaries from noisy proposals in a denoising diffusion process, conditioned on a target audio sample. During training, our model learns to reverse the noising process by converting noisy latent queries to the ground-truth versions in the elegant Transformer decoder framework. Doing so enables the model generate accurate event boundaries from even noisy queries during inference. Extensive experiments on the Urban-SED and EPIC-Sounds datasets demonstrate that our model significantly outperforms existing alternatives, with 40+% faster convergence in training. Code: https://github.com/Surrey-UPLab/DiffSED

Source-Free Domain Adaptation (SFDA) aims to adapt a source model for a target domain, with only access to unlabeled target training data and the source model pretrained on a supervised source domain. Relying on pseudo labeling and/or auxiliary supervision, conventional methods are inevitably error-prone. To mitigate this limitation, in this work we for the first time explore the potentials of off-the-shelf vision-language (ViL) multimodal models (e.g., CLIP) with rich whilst heterogeneous knowledge. We find that directly applying the ViL model to the target domain in a zero-shot fashion is unsatisfactory, as it is not specialized for this particular task but largely generic. To make it task specific, we propose a novel Distilling multImodal Foundation mOdel (DIFO) approach. Specifically, DIFO alternates between two steps during adaptation: (i) Customizing the ViL model by maximizing the mutual information with the target model in a prompt learning manner, (ii) Distilling the knowledge of this customized ViL model to the target model. For more fine-grained and reliable distillation, we further introduce two effective regularization terms, namely most-likely category encouragement and predictive consistency. Extensive experiments show that DIFO significantly outperforms the state-of-the-art alternatives. Code is here.

High-resolution 3D object generation remains a challenging task primarily due to the limited availability of comprehensive annotated training data. Recent advancements have aimed to overcome this constraint by harnessing image generative models, pretrained on extensive curated web datasets, using knowledge transfer techniques like Score Distillation Sampling (SDS). Efficiently addressing the requirements of high-resolution rendering often necessitates the adoption of latent representation-based models, such as the Latent Diffusion Model (LDM). In this framework, a significant challenge arises: To compute gradients for individual image pixels, it is necessary to backpropagate gradients from the designated latent space through the frozen components of the image model, such as the VAE encoder used within LDM. However, this gradient propagation pathway has never been optimized, remaining uncontrolled during training. We find that the unregulated gradients adversely affect the 3D model's capacity in acquiring texture-related information from the image generative model, leading to poor quality appearance synthesis. To address this overarching challenge, we propose an innovative operation termed Pixel-wise Gradient Clipping (PGC) designed for seamless integration into existing 3D generative models, thereby enhancing their synthesis quality. Specifically, we control the magnitude of stochastic gradients by clipping the pixel-wise gradients efficiently, while preserving crucial texture-related gradient directions. Despite this simplicity and minimal extra cost, extensive experiments demonstrate the efficacy of our PGC in enhancing the performance of existing 3D generative models for high-resolution object rendering.

Black-box domain adaptation treats the source domain model as a black box. During the transfer process, the only available information about the target domain is the noisy labels output by the black-box model. This poses significant challenges for domain adaptation. Conventional approaches typically tackle the black-box noisy label problem from two aspects: self-knowledge distillation and pseudo-label denoising, both achieving limited performance due to limited knowledge information. To mitigate this issue, we explore the potential of off-the-shelf vision-language (ViL) multimodal models with rich semantic information for black-box domain adaptation by introducing an Adversarial Experts Model (AEM). Specifically, our target domain model is designed as one feature extractor and two classifiers, trained over two stages: In the knowledge transferring stage, with a shared feature extractor, the black-box source model and the ViL model act as two distinct experts for joint knowledge contribution, guiding the learning of one classifier each. While contributing their respective knowledge, the experts are also updated due to their own limitation and bias. In the adversarial alignment stage, to further distill expert knowledge to the target domain model, adversarial learning is conducted between the feature extractor and the two classifiers. A new consistency-max loss function is proposed to measure two classifier consistency and further improve classifier prediction certainty. Extensive experiments on multiple datasets demonstrate the effectiveness of our approach. Code is available at https://github.com/singinger/AEM.

Novel view acoustic synthesis (NVAS) aims to render binaural audio at any target viewpoint, given a mono audio emitted by a sound source at a 3D scene. Existing methods have proposed NeRF-based implicit models to exploit visual cues as a condition for synthesizing binaural audio. However, in addition to low efficiency originating from heavy NeRF rendering, these methods all have a limited ability of characterizing the entire scene environment such as room geometry, material properties, and the spatial relation between the listener and sound source. To address these issues, we propose a novel Audio-Visual Gaussian Splatting (AV-GS) model. To obtain a material-aware and geometry-aware condition for audio synthesis, we learn an explicit point-based scene representation with audio-guidance parameters on locally initialized Gaussian points, taking into account the space relation from the listener and sound source. To make the visual scene model audio adaptive, we propose a point densification and pruning strategy to optimally distribute the Gaussian points, with the per-point contribution in sound propagation (e.g., more points needed for texture-less wall surfaces as they affect sound path diversion). Extensive experiments validate the superiority of our AV-GS over existing alternatives on the real-world RWAS and simulation-based SoundSpaces datasets. Project page: \url{https://surrey-uplab.github.io/research/avgs/}

3D representation is essential to the significant advance of 3D generation with 2D diffusion priors. As a flexible representation, NeRF has been first adopted for 3D representation. With density-based volumetric rendering, it however suffers both intensive computational overhead and inaccurate mesh extraction. Using a signed distance field and Marching Tetrahedra, DMTet allows for precise mesh extraction and real-time rendering but is limited in handling large topological changes in meshes, leading to optimization challenges. Alternatively, 3D Gaussian Splatting (3DGS) is favored in both training and rendering efficiency while falling short in mesh extraction. In this work, we introduce a novel 3D representation, Tetrahedron Splatting (TeT-Splatting), that supports easy convergence during optimization, precise mesh extraction, and real-time rendering simultaneously. This is achieved by integrating surface-based volumetric rendering within a structured tetrahedral grid while preserving the desired ability of precise mesh extraction, and a tile-based differentiable tetrahedron rasterizer. Furthermore, we incorporate eikonal and normal consistency regularization terms for the signed distance field to improve generation quality and stability. Critically, our representation can be trained without mesh extraction, making the optimization process easier to converge. Our TeT-Splatting can be readily integrated in existing 3D generation pipelines, along with polygonal mesh for texture optimization. Extensive experiments show that our TeT-Splatting strikes a superior tradeoff among convergence speed, render efficiency, and mesh quality as compared to previous alternatives under varying 3D generation settings.

We propose to explore an interesting and promising problem, Cloud Object Detector Adaptation (CODA), where the target domain leverages detections provided by a large cloud model to build a target detector. Despite with powerful generalization capability, the cloud model still cannot achieve error-free detection in a specific target domain. In this work, we present a novel Cloud Object detector adaptation method by Integrating different source kNowledge (COIN). The key idea is to incorporate a public vision-language model (CLIP) to distill positive knowledge while refining negative knowledge for adaptation by self-promotion gradient direction alignment. To that end, knowledge dissemination, separation, and distillation are carried out successively. Knowledge dissemination combines knowledge from cloud detector and CLIP model to initialize a target detector and a CLIP detector in target domain. By matching CLIP detector with the cloud detector, knowledge separation categorizes detections into three parts: consistent, inconsistent and private detections such that divide-and-conquer strategy can be used for knowledge distillation. Consistent and private detections are directly used to train target detector; while inconsistent detections are fused based on a consistent knowledge generation network, which is trained by aligning the gradient direction of inconsistent detections to that of consistent detections, because it provides a direction toward an optimal target detector. Experiment results demonstrate that the proposed COIN method achieves the state-of-the-art performance.

Motion forecasting for agents in autonomous driving is highly challenging due to the numerous possibilities for each agent's next action and their complex interactions in space and time. In real applications, motion forecasting takes place repeatedly and continuously as the self-driving car moves. However, existing forecasting methods typically process each driving scene within a certain range independently, totally ignoring the situational and contextual relationships between successive driving scenes. This significantly simplifies the forecasting task, making the solutions suboptimal and inefficient to use in practice. To address this fundamental limitation, we propose a novel motion forecasting framework for continuous driving, named RealMotion. It comprises two integral streams both at the scene level: (1) The scene context stream progressively accumulates historical scene information until the present moment, capturing temporal interactive relationships among scene elements. (2) The agent trajectory stream optimizes current forecasting by sequentially relaying past predictions. Besides, a data reorganization strategy is introduced to narrow the gap between existing benchmarks and real-world applications, consistent with our network. These approaches enable exploiting more broadly the situational and progressive insights of dynamic motion across space and time. Extensive experiments on Argoverse series with different settings demonstrate that our RealMotion achieves state-of-the-art performance, along with the advantage of efficient real-world inference.

Understanding the semantics of individual regions or patches of unconstrained images, such as open-world object detection, remains a critical yet challenging task in computer vision. Building on the success of powerful image-level vision-language (ViL) foundation models like CLIP, recent efforts have sought to harness their capabilities by either training a contrastive model from scratch with an extensive collection of region-label pairs or aligning the outputs of a detection model with image-level representations of region proposals. Despite notable progress, these approaches are plagued by computationally intensive training requirements, susceptibility to data noise, and deficiency in contextual information. To address these limitations, we explore the synergistic potential of off-the-shelf foundation models, leveraging their respective strengths in localization and semantics. We introduce a novel, generic, and efficient architecture, named RegionSpot, designed to integrate position-aware localization knowledge from a localization foundation model (e.g., SAM) with semantic information from a ViL model (e.g., CLIP). To fully exploit pretrained knowledge while minimizing training overhead, we keep both foundation models frozen, focusing optimization efforts solely on a lightweight attention-based knowledge integration module. Extensive experiments in open-world object recognition show that our RegionSpot achieves significant performance gain over prior alternatives, along with substantial computational savings (e.g., training our model with 3 million data in a single day using 8 V100 GPUs). RegionSpot outperforms GLIP-L by 2.9 in mAP on LVIS val set, with an even larger margin of 13.1 AP for more challenging and rare categories, and a 2.5 AP increase on ODinW. Furthermore, it exceeds GroundingDINO-L by 11.0 AP for rare categories on the LVIS minival set.

Abstract Existing Source-Free Domain Adaptation (SFDA) methods typically adopt the feature distribution alignment paradigm via mining auxiliary information (eg., pseudo-labelling, source domain data generation). However, they are largely limited due to that the auxiliary information is usually error-prone whilst lacking effective error-mitigation mechanisms. To overcome this fundamental limitation, in this paper we propose a novel Target Prediction Distribution Searching (TPDS) paradigm. Theoretically, we prove that in case of sufficient small distribution shift, the domain transfer error could be well bounded. To satisfy this condition, we introduce a flow of proxy distributions that facilitates the bridging of typically large distribution shift from the source domain to the target domain. This results in a progressive searching on the geodesic path where adjacent proxy distributions are regularized to have small shift so that the overall errors can be minimized. To account for the sequential correlation between proxy distributions, we develop a new pairwise alignment with category consistency algorithm for minimizing the adaptation errors. Specifically, a manifold geometry guided cross-distribution neighbour search is designed to detect the data pairs supporting the Wasserstein distance based shift measurement. Mutual information maximization is then adopted over these pairs for shift regularization. Extensive experiments on five challenging SFDA benchmarks show that our TPDS achieves new state-of-the-art performance. The code and datasets are available at https://github.com/tntek/TPDS .

State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model's generalizability in the limited-label regime.Semi-supervised learning and unsupervised learning offer promising paradigms to learn from an abundance of unlabeled visual data. Recent progress in these paradigms has indicated the strong benefits of leveraging unlabeled data to improve model generalization and provide better model initialization. In this survey, we review the recent advanced deep learning algorithms on semi-supervised learning (SSL) and unsupervised learning (UL) for visual recognition from a unified perspective. To offer a holistic understanding of the state-of-the-art in these areas, we propose a unified taxonomy. We categorize existing representative SSL and UL with comprehensive and insightful analysis to highlight their design rationales in different learning scenarios and applications in different computer vision tasks. Lastly, we discuss the emerging trends and open challenges in SSL and UL to shed light on future critical research directions.

The new generation of organic light emitting diode display is designed to enable the high dynamic range (HDR), going beyond the standard dynamic range (SDR) supported by the traditional display devices. However, a large quantity of videos are still of SDR format. Further, most pre-existing videos are compressed at varying degrees for minimizing the storage and traffic flow demands. To enable movie-going experience on new generation devices, converting the compressed SDR videos to the HDR format (i.e., compressed-SDR to HDR conversion) is in great demands. The key challenge with this new problem is how to solve the intrinsic many-to-many mapping issue. However, without constraining the solution space or simply imitating the inverse camera imaging pipeline in stages, existing SDR-to-HDR methods can not formulate the HDR video generation process explicitly. Besides, they ignore the fact that videos are often compressed. To address these challenges, in this work we propose a novel imaging knowledge-inspired parallel networks (termed as KPNet) for compressed-SDR to HDR (CSDR-to-HDR) video reconstruction. KPNet has two key designs: Knowledge-Inspired Block (KIB) and Information Fusion Module (IFM). Concretely, mathematically formulated using some priors with compressed videos, our conversion from a CSDR-to-HDR video reconstruction is conceptually divided into four synergistic parts: reducing compression artifacts, recovering missing details, adjusting imaging parameters, and reducing image noise. We approximate this process by a compact KIB. To capture richer details, we learn HDR representations with a set of KIBs connected in parallel and fused with the IFM. Extensive evaluations show that our KPNet achieves superior performance over the state-of-the-art methods.

Pedestrian detection is an important task in computer vision, which is also an important part of intelligent transportation systems. For privacy protection, thermal images are widely used in pedestrian detection problems. However, thermal pedestrian detection is challenging due to the significant effect of temperature variation on the illumination of images and that fine-grained illumination annotations are difficult to be acquired. The existing methods have attempted to exploit coarse-grained day/night labels, which however even hampers the model performance. In this work, we introduce a novel idea of regressing conditional thermal-visible feature distribution, dubbed as Illumination Distribution-Aware adaptation (IDA). The key idea is to predict the conditional visible feature distribution given a thermal image, subject to their pre-computed joint distribution. Specifically, we first estimate the thermal-visible feature joint distribution by constructing feature co-occurrence matrices, offering a conditional probability distribution for any given thermal image. With this pairing information, we then form a conditional probability distribution regression task for model optimization. Critically, as a model agnostic strategy, this allows the visible feature knowledge to be transferred to the thermal counterpart implicitly for learning more discriminating feature representation. Experiment results show that our method outperforms the prior art methods, which use extra illumination annotations. Besides, as a plug-in, our method can averagely reduce about 2% MR on KAIST dataset, and improve about 1% mAP on FLIR-aligned and Autonomous Vehicles datasets without extra calculation for test. Code is available athttps://github.com/HaMeow-lst1/IDA.

3D object detection in autonomous driving aims to reason “what” and “where” the objects of interest present in a 3D world. Following the conventional wisdom of previous 2D object detection, existing methods often adopt the canonical Cartesian coordinate system with perpendicular axis. However, we conjugate that this does not fit the nature of the ego car’s perspective, as each onboard camera perceives the world in shape of wedge intrinsic to the imaging geometry with radical (non perpendicular) axis. Hence, in this paper we advocate the exploitation of the Polar coordinate system and propose a new Polar Transformer (PolarFormer) for more accurate 3D object detection in the bird’s-eye-view (BEV) taking as input only multi-camera 2D images. Specifically, we design a cross-attention based Polar detection head without restriction to the shape of input structure to deal with irregular Polar grids. For tackling the unconstrained object scale variations along Polar’s distance dimension, we further introduce a multi-scale Polar representation learning strategy. As a result, our model can make best use of the Polar representation rasterized via attending to the corresponding image observation in a sequence-to-sequence fashion subject to the geometric constraints. Thorough experiments on the nuScenes dataset demonstrate that our PolarFormer outperforms significantly state-of-the-art 3D object detection alternatives.

We present Generative Semantic Segmentation (GSS), a generative learning approach for semantic segmentation. Uniquely, we cast semantic segmentation as an image-conditioned mask generation problem. This is achieved by replacing the conventional per-pixel discriminative learning with a latent prior learning process. Specifically, we model the variational posterior distribution of latent vari-ables given the segmentation mask. To that end, the segmentation mask is expressed with a special type of image (dubbed as maskige). This posterior distribution allows to generate segmentation masks unconditionally. To achieve semantic segmentation on a given image, we further intro-duce a conditioning network. It is optimized by minimizing the divergence between the posterior distribution of maskige (i.e. segmentation masks) and the latent prior distribution of input training images. Extensive experiments on standard benchmarks show that our GSS can perform competitively to prior art alternatives in the standard semantic segmentation setting, whilst achieving a new state of the art in the more challenging cross-domain setting.

In the fashion domain, there exists a variety of vision-and-language (V+L) tasks, including cross-modal retrieval, text-guided image retrieval, multi-modal classification, and image captioning. They differ drastically in each individual input/output format and dataset size. It has been common to design a task-specific model and fine-tune it independently from a pre-trained V+l model (e.g., CLIP). This results in parameter inefficiency and inability to exploit inter-task relatedness. To address such issues, we propose a novel FAshion-focused Multi-task Efficient learning method for Vision-and-Language tasks (FAME-ViL) in this work. Compared with existing approaches, FAME-ViL applies a single model for multiple heterogeneous fashion tasks, therefore being much more parameter-efficient. It is enabled by two novel components: (1) a task-versatile architecture with cross-attention adapters and task-specific adapters integrated into a unified V+L model, and (2) a stable and effective multi-task training strategy that supports learning from heterogeneous data and prevents negative transfer. Extensive experiments on four fashion tasks show that our FAME-ViL can save 61.5% of parameters over alternatives, while significantly outperforming the conventional independently trained single-task models. Code is available at https://github.com/BrandonHanx/FAME-ViL.

Existing Temporal Action Detection (TAD) methods typically take a pre-processing step in converting an input varying-length video into a fixed-length snippet representation sequence, before temporal boundary estimation and action classification. This pre-processing step would temporally downsample the video, reducing the inference resolution and hampering the detection performance in the original temporal resolution. In essence, this is due to a temporal quantization error introduced during resolution downsampling and recovery. This could negatively impact the TAD performance, but is largely ignored by existing methods. To address this problem, in this work we introduce a novel model-agnostic post-processing method without model redesign and retraining. Specifically, we model the start and end points of action instances with a Gaussian distribution for enabling temporal boundary inference at a sub-snippet level. We further introduce an efficient Taylor-expansion based approximation, dubbed as Gaussian Approximated Post-processing (GAP). Extensive experiments demonstrate that our GAP can consistently improve a wide variety of pre-trained off-the-shelf TAD models on the challenging ActivityNet (+0.2%~0. 7% in average mAP) and THUMOS (+0.2%~0.5% in average mAP) benchmarks. Such performance gains are already significant and highly comparable to those achieved by novel model designs. Also, GAP can be integrated with model training for further performance gain. Importantly, GAP enables lower temporal resolutions for more efficient inference, facilitating low-resource application. The code is available at https://github.com/sauradip/GAP

Controllable person image synthesis aims at rendering a source image based on user-specified changes in body pose or appearance. Prior art approaches leverage pixel-level denoising diffusion models conditioned on the coarse skeleton via cross-attention. This leads to two limitations: low efficiency and inaccurate condition information. To address both issues, a novel Pose-Constrained Latent Diffusion model (PoCoLD) is introduced. Rather than using the skeleton as a sparse pose representation, we exploit DensePose which offers much richer body structure information. To effectively capitalize DensePose at a low cost, we propose an efficient pose-constrained attention module that is capable of modeling the complex interplay between appearance and pose. Extensive experiments show that our PoCoLD outperforms the state-of-the-art competitors in image synthesis fidelity. Critically, it runs 2× faster and consumes 3.6× smaller memory than the latest diffusion-model-based alternative during inference. Our code and models are available at https://github.com/BrandonHanx/PoCoLD.

We propose a new formulation of temporal action detection (TAD) with denoising diffusion, DiffTAD in short. Taking as input random temporal proposals, it can yield action proposals accurately given an untrimmed long video. This presents a generative modeling perspective, against previous discriminative learning manners. This capability is achieved by first diffusing the ground-truth proposals to random ones (i.e., the forward/noising process) and then learning to reverse the noising process (i.e., the backward/denoising process). Concretely, we establish the denoising process in the Transformer decoder (e.g., DETR) by introducing a temporal location query design with faster convergence in training. We further propose a cross-step selective conditioning algorithm for inference acceleration. Extensive evaluations on ActivityNet and THUMOS show that our DiffTAD achieves top performance compared to previous art alternatives. The code is available at https://github.com/sauradip/DiffusionTAD.

Long-term re-id with clothes change is a challenging problem in surveillance AI. Currently, its major bottleneck is that this field is still missing a large realistic benchmark. In this work, we contribute a large, realistic long-term person re-identification benchmark, termed DeepChange. Its unique characteristics are: (1) Realistic and rich personal appearance (e.g., clothes and hair style) and variations: Highly diverse clothes change and styles, with varying reappearing gaps in time from minutes to seasons, different weather conditions (e.g., sunny, cloudy, windy, rainy, snowy, extremely cold) and events (e.g., working, leisure, daily activities). (2) Rich camera setups: Raw videos were recorded by 17 outdoor varying-resolution cameras operating in a real-world surveillance system. (3) The currently largest number of (17) cameras, (1, 121) identities, and (178, 407) bounding boxes, over the longest time span (12 months). We benchmark the representative supervised and unsupervised re-id methods on our dataset. In addition, we investigate multimodal fusion strategies for tackling the clothes change challenge. Extensive experiments show that our fusion models outperform a wide variety of state-of-the-art models on DeepChange. Our dataset and documents are available at https://github.com/PengBoXiangShang/deepchange.

Existing unsupervised domain adaptation (UDA) methods rely on aligning the features from the source and target domains explicitly or implicitly in a common space (i.e., the domain invariant space). Explicit distribution matching ignores the discriminability of learned features, while the implicit counterpart such as self-supervised learning suffers from pseudo-label noises. With distribution alignment, it is challenging to acquire a common space which maintains fully the discriminative structure of both domains. In this work, we propose a novel HomeomorphisM Alignment (HMA) approach characterized by aligning the source and target data in two separate spaces. Specifically, an invertible neural network based homeomorphism is constructed. Distribution matching is then used as a sewing up tool for connecting this homeomorphism mapping between the source and target feature spaces. Theoretically, we show that this mapping can preserve the data topological structure (e.g., the cluster/group structure). This property allows for more discriminative model adaptation by leveraging both the original and transformed features of source data in a supervised manner, and those of target domain in an unsupervised manner (e.g., prediction consistency). Extensive experiments demonstrate that our method can achieve the state-of-the-art results. Code is released at https://github.com/buerzlh/HMA.

Existing Unsupervised Domain Adaptation (UDA) methods typically attempt to perform knowledge transfer in a domain-invariant space explicitly or implicitly. In practice, however, the obtained features is often mixed with domain-specific information which causes performance degradation. To overcome this fundamental limitation, this article presents a novel independent feature decomposition and instance alignment method (IndUDA in short). Specifically, based on an invertible flow, we project the base features into a decomposed latent space with domain-invariant and domain-specific dimensions. To drive semantic decomposition independently, we then swap the domain-invariant part across source and target domain samples with the same category and require their inverted features are consistent in class-level with the original features. By treating domain-specific information as noise, we replace it by Gaussian noise and further regularize source model training by instance alignment, i.e., requiring the base features close to the corresponding reconstructed features, respectively. Extensive experiment results demonstrate that our method achieves state-of-the-art performance on popular UDA benchmarks. The appendix and code are available at https://github.com/ayombeach/IndUDA.

Recently, text-guided 3D generative methods have made remarkable advancements in producing high-quality textures and geometry, capitalizing on the proliferation of large vision-language and image diffusion models. However, existing methods still struggle to create high-fidelity 3D head avatars in two aspects: (1) They rely mostly on a pre-trained text-to-image diffusion model whilst missing the necessary 3D awareness and head priors. This makes them prone to inconsistency and geometric distortions in the generated avatars. (2) They fall short in fine-grained editing. This is primarily due to the inherited limitations from the pre-trained 2D image diffusion models, which become more pronounced when it comes to 3D head avatars. In this work, we address these challenges by introducing a versatile coarse-to-fine pipeline dubbed HeadSculpt for crafting (i.e., generating and editing) 3D head avatars from textual prompts. Specifically, we first equip the diffusion model with 3D awareness by leveraging landmark-based control and a learned textual embedding representing the back view appearance of heads, enabling 3D-consistent head avatar generations. We further propose a novel identity-aware editing score distillation strategy to optimize a textured mesh with a high-resolution differentiable rendering technique. This enables identity preservation while following the editing instruction. We showcase HeadSculpt's superior fidelity and editing capabilities through comprehensive experiments and comparisons with existing methods.

Transformer is a promising neural network learner, and has achieved great success in various machine learning tasks. Thanks to the recent prevalence of multimodal applications and Big Data, Transformer-based multimodal learning has become a hot topic in AI research. This paper presents a comprehensive survey of Transformer techniques oriented at multimodal data. The main contents of this survey include: (1) a background of multimodal learning, Transformer ecosystem, and the multimodal Big Data era, (2) a systematic review of Vanilla Transformer, Vision Transformer, and multimodal Transformers, from a geometrically topological perspective, (3) a review of multimodal Transformer applications, via two important paradigms, i.e., for multimodal pretraining and for specific multimodal tasks, (4) a summary of the common challenges and designs shared by the multimodal Transformer models and applications, and (5) a discussion of open problems and potential research directions for the community.

Existing neural architecture search (NAS) methods usually explore a limited feature-transformation-only search space, ignoring other advanced feature operations such as feature self-calibration by attention and dynamic convolutions. This disables the NAS algorithms to discover more advanced network architectures. We address this limitation by additionally exploiting feature self-calibration operations, resulting in a heterogeneous search space. To solve the challenges of operation heterogeneity and significantly larger search space, we formulate a neural operator search (NOS) method. NOS presents a novel heterogeneous residual block for integrating the heterogeneous operations in a unified structure, and an attention guided search strategy for facilitating the search process over a vast space. Extensive experiments show that NOS can search novel cell architectures with highly competitive performance on the CIFAR and ImageNet benchmarks.

Unsupervised domain adaptation aims to transfer knowledge from labeled source domain to unlabeled target domain. The semi-supervised method based on mean-teacher framework is one of the main stream approaches. By enforcing consistency constraints, it is hopeful that the teacher network will distill useful source domain knowledge to the student network. However, in practice negative transfer often emerges because the performance of the teacher network is not guaranteed to be always better than the student network. To address this limitation, a novel Adaptive Mutual Learning (AML) strategy is proposed in this paper. Specifically, given a target sample, the network with worse prediction will be optimized by pushing its prediction close to the better prediction. This is in the spirit of traditional knowledge distillation. On the other hand, the network with better prediction is further refined by requiring its prediction to stay away from the worse prediction. This can be regarded conceptually as reverse knowledge distillation. In this way, two networks learn from each other according to their respective performance. At inference phase, the averaged output of these two networks can be taken as the final prediction. Experimental results demonstrate that our AML achieves competitive results.

Source-free object detection (SFOD) needs to adapt a detector pre-trained on a labeled source domain to a tar-get domain, with only unlabeled training data from the tar-get domain. Existing SFOD methods typically adopt the pseudo labeling paradigm with model adaption alternating between predicting pseudo labels and fine-tuning the model. This approach suffers from both unsatisfactory accuracy of pseudo labels due to the presence of domain shift and lim-ited use of target domain training data. In this work, we present a novel Learning to Overlook Domain Style (LODS) method with such limitations solved in a principled man-ner. Our idea is to reduce the domain shift effect by en-forcing the model to overlook the target domain style, such that model adaptation is simplified and becomes easier to carry on. To that end, we enhance the style of each tar-get domain image and leverage the style degree difference between the original image and the enhanced image as a self-supervised signal for model adaptation. By treating the enhanced image as an auxiliary view, we exploit a student- teacher architecture for learning to overlook the style de-gree difference against the original image, also character-ized with a novel style enhancement algorithm and graph alignment constraint. Extensive experiments demonstrate that our LODS yields new state-of-the-art performance on four benchmarks.

Semantic understanding of 3D point cloud relies on learning models with massively annotated data, which, in many cases, are expensive or difficult to collect. This has led to an emerging research interest in semi-supervised learning (SSL) for 3D point cloud. It is commonly assumed in SSL that the unlabeled data are drawn from the same distribution as that of the labeled ones; This assumption, however, rarely holds true in realistic environments. Blindly using out-of-distribution (OOD) unlabeled data could harm SSL performance. In this work, we propose to selectively utilize unlabeled data through sample weighting, so that only conducive unlabeled data would be prioritized. To estimate the weights, we adopt a bi-level optimization framework which iteratively optimizes a meta-objective on a held-out validation set and a task-objective on a training set. Faced with the instability of efficient bi-level optimizers, we further propose three regularization techniques to enhance the training stability. Extensive experiments on 3D point cloud classification and segmentation tasks verify the effectiveness of our proposed method. We also demonstrate the feasibility of a more efficient training strategy. Our code is released on Github1.

Recently, with the rise of high dynamic range (HDR) display devices, there is a great demand to transfer traditional low dynamic range (LDR) images into HDR versions. The key to success is how to solve the many-to-many mapping problem. However, the existing approaches either do not consider constraining solution space or just simply imitate the inverse camera imaging pipeline in stages, without directly formulating the HDR image generation process. In this work, we address this problem by integrating LDR-to-HDR imaging knowledge into an UNet architecture, dubbed as Knowledge-inspired UNet (KUNet). The conversion from LDR-to-HDR image is mathematically formulated, and can be conceptually divided into recovering missing details, adjusting imaging parameters and reducing imaging noise. Accordingly, we develop a basic knowledge-inspired block (KIB) including three subnetworks corresponding to the three procedures in this HDR imaging process. The KIB blocks are cascaded in the similar way to the UNet to construct HDR image with rich global information. In addition, we also propose a knowledge inspired jump-connect structure to fit a dynamic range gap between HDR and LDR images. Experimental results demonstrate that the proposed KUNet achieves superior performance compared with the state-of-the-art methods. The code, dataset and appendix materials are available at https://github.com/wanghu178/KUNet.git.

Following the conventional hybrid video coding framework, existing learned video compression methods rely on the decoded previous frame as the reference for motion estimation considering that it is available to the decoder. Diving into its essential advantage of strong representation capability with CNNs, however, we find this strategy is suboptimal due to two reasons: (1) Motion estimation based on the decoded (often distorted) frame would damage both the spatial structure of motion information inferred and the corresponding residual for each frame, making it difficult to be spatially encoded on the whole image basis using CNNs; (2) Typically, it would break the consistent nature across frames since the estimated motion information is no longer consistent with the movement in the original video due to the distortion in the decoded video, lowering the overall temporal coding efficiency. To overcome these problems, a novel asymmetric Structure-Preserving Motion Estimation (SPME) method is proposed, with the aim to fully explore the ignored original previous frame at the encoder side while complying with the decoded previous frame at the decoder side. Concretely, SPME estimates superior spatially structure-preserving and temporally consistent motion field by aggregating the motion prediction of both the original and the decoded reference frames w.r.t the current frame. Critically, our method can be universally applied to the existing feature prediction based video compression methods. Extensive experiments on several standard test datasets show that our SPME can significantly enhance the state-of-the-art methods.

As a state-of-the-art family of Unsupervised Domain Adaptation (UDA), bi-classifier adversarial learning methods are formulated in an adversarial (minimax) learning framework with a single feature extractor and two classifiers. Model training alternates between two steps: (I) constraining the learning of the two classifiers to maximize the prediction discrepancy of unlabeled target domain data, and (II) constraining the learning of the feature extractor to minimize this discrepancy. Despite being an elegant formulation, this approach has a fundamental limitation: Maximizing and minimizing the classifier discrepancy is not class discriminative for the target domain, finally leading to a suboptimal adapted model. To solve this problem, we propose a novel Class Discriminative Adversarial Learning (CDAL) method characterized by discovering class discrimination knowledge and leveraging this knowledge to discriminatively regulate the classifier discrepancy constraints on-the-fly. This is realized by introducing an evaluation criterion for judging each classifier's capability and each target domain sample's feature reorientation via objective loss reformulation. Extensive experiments on three standard benchmarks show that our CDAL method yields new state-of-the-art performance. Our code is made available at https://github.com/buerzlh/CDAL.

Capitalizing on large pre-trained models for various downstream tasks of interest have recently emerged with promising performance. Due to the ever-growing model size, the standard full fine-tuning based task adaptation strategy becomes prohibitively costly in terms of model training and storage. This has led to a new research direction in parameter-efficient transfer learning. However, existing attempts typically focus on downstream tasks from the same modality (e.g., image understanding) of the pre-trained model. This creates a limit because in some specific modalities, (e.g., video understanding) such a strong pre-trained model with sufficient knowledge is less or not available. In this work, we investigate such a novel cross-modality transfer learning setting, namely parameter-efficient image-to-video transfer learning. To solve this problem, we propose a new Spatio-Temporal Adapter (ST-Adapter) for parameter-efficient fine-tuning per video task. With a built-in spatio-temporal reasoning capability in a compact design, ST-Adapter enables a pre-trained image model without temporal knowledge to reason about dynamic video content at a small ~8% per-task parameter cost, requiring approximately 20 times fewer updated parameters compared to previous work. Extensive experiments on video action recognition tasks show that our ST-Adapter can match or even outperform the strong full fine-tuning strategy and state-of-the-art video models, whilst enjoying the advantage of parameter efficiency.

In medical image analysis, we often need to build an image recognition system for a target scenario with the access to small labeled data and abundant unlabeled data, as well as multiple related models pretrained on different source scenarios. This presents the combined challenges of multi-source-free domain adaptation and semi-supervised learning simultaneously. However, both problems are typically studied independently in the literature, and how to effectively combine existing methods is non-trivial in design. In this work, we introduce a novel MetaTeacher framework with three key components: (1) A learnable coordinating scheme for adaptive domain adaptation of individual source models, (2) A mutual feedback mechanism between the target model and source models for more coherent learning, and (3) A semi-supervised bilevel optimization algorithm for consistently organizing the adaption of source models and the learning of target model. It aims to leverage the knowledge of source models adaptively whilst maximize their complementary benefits collectively to counter the challenge of limited supervision. Extensive experiments on five chest x-ray image datasets show that our method outperforms clearly all the state-of-the-art alternatives. The code is available at https://github.com/wongzbb/metateacher.

Existing top-performance 3D object detectors typically rely on the multi-modal fusion strategy. This design is however fundamentally restricted due to overlooking the modality-specific useful information and finally hampering the model performance. To address this limitation, in this work we introduce a novel modality interaction strategy where individual per-modality representations are learned and maintained throughout for enabling their unique characteristics to be exploited during object detection. To realize this proposed strategy, we design a DeepInteraction architecture characterized by a multi-modal representational interaction encoder and a multi-modal predictive interaction decoder. Experiments on the large-scale nuScenes dataset show that our proposed method surpasses all prior arts often by a large margin. Crucially, our method is ranked at the first position at the highly competitive nuScenes object detection leaderboard.

Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain, given labeled data on a source domain whose distribution diverges from the target one. Mainstream UDA methods strive to learn domain-aligned features such that classifiers trained on the source features can be readily applied to the target ones. Although impressive results have been achieved, these methods have a potential risk of damaging the intrinsic data structures of target discrimination, raising an issue of generalization particularly for UDA tasks in an inductive setting. To address this issue, we are motivated by a UDA assumption of structural similarity across domains, and propose to directly uncover the intrinsic target discrimination via constrained clustering, where we constrain the clustering solutions using structural source regularization that hinges on the very same assumption. Technically, we propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one, and we thus term our method as H-SRDC. Our hybrid model is based on a deep clustering framework that minimizes the Kullback-Leibler divergence between the distribution of network prediction and an auxiliary one, where we impose structural regularization by learning domain-shared classifier and cluster centroids. By enriching the structural similarity assumption, we are able to extend H-SRDC for a pixel-level UDA task of semantic segmentation. We conduct extensive experiments on seven UDA benchmarks of image classification and semantic segmentation. With no explicit feature alignment, our proposed H-SRDC outperforms all the existing methods under both the inductive and transductive settings. We make our implementation codes publicly available at https://github.com/huitangtang/H-SRDC.

Most existing person re-identification (re-id) methods assume supervised model training on a separate large set of training samples from the target domain. While performing well in the training domain, such trained models are seldom generalisable to a new independent unsupervised target domain without further labelled training data from the target domain. To solve this scalability limitation, we develop a novel Hierarchical Unsupervised Domain Adaptation (HUDA) method. It can transfer labelled information of an existing dataset (a source domain) to an unlabelled target domain for unsupervised person re-id. Specifically, HUDA is designed to model jointly global distribution alignment and local instance alignment in a two-level hierarchy for discovering transferable source knowledge in unsupervised domain adaptation. Crucially, this approach aims to overcome the under-constrained learning problem of existing unsupervised domain adaptation methods. Extensive evaluations show the superiority of HUDA for unsupervised cross-domain person re-id over a wide variety of state-of-the-art methods on four re-id benchmarks: Market-1501, DukeMTMC, MSMT17 and CUHK03.

Human pose estimation has achieved significant progress on images with high imaging resolution. However, low-resolution imagery data bring nontrivial challenges which are still under-studied. To fill this gap, we start with investigating existing methods and reveal that the most dominant heatmap-based methods would suffer more severe model performance degradation from low-resolution, and offset learning is an effective strategy. Established on this observation, in this work we propose a novel Confidence-Aware Learning (CAL) method which further addresses two fundamental limitations of existing offset learning methods: inconsistent training and testing, decoupled heatmap and offset learning. Specifically, CAL selectively weighs the learning of heatmap and offset with respect to ground-truth and most confident prediction, whilst capturing the statistical importance of model output in mini-batch learning manner. Extensive experiments conducted on the COCO benchmark show that our method outperforms significantly the state-of-the-art methods for low-resolution human pose estimation.

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer (i.e., without convolution and resolution reduction) to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR). Extensive experiments show that SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes. Particularly, we achieve the first position in the highly competitive ADE20K test server leaderboard on the day of submission.

A few-shot semantic segmentation model is typically composed of a CNN encoder, a CNN decoder and a simple classifier (separating foreground and background pixels). Most existing methods meta-learn all three model components for fast adaptation to a new class. However, given that as few as a single support set image is available, effective model adaption of all three components to the new class is extremely challenging. In this work we propose to simplify the meta-learning task by focusing solely on the simplest component – the classifier, whilst leaving the en-coder and decoder to pre-training. We hypothesize that if we pretrain an off-the-shelf segmentation model over a set of diverse training classes with sufficient annotations, the encoder and decoder can capture rich discriminative features applicable for any unseen classes, rendering the sub-sequent meta-learning stage unnecessary. For the classifier meta-learning, we introduce a Classifier Weight Transformer (CWT) designed to dynamically adapt the support-set trained classifier’s weights to each query image in an inductive way. Extensive experiments on two standard bench-marks show that despite its simplicity, our method outperforms the state-of-the-art alternatives, often by a large margin. Code is available on https://github.com/zhiheLu/CWT-for-FSS.

Many video analysis tasks require temporal localization for the detection of content changes. However, most existing models developed for these tasks are pre-trained on general video action classification tasks. This is due to large scale annotation of temporal boundaries in untrimmed videos being expensive. Therefore, no suitable datasets exist that enable pre-training in a manner sensitive to temporal boundaries. In this paper for the first time, we investigate model pre-training for temporal localization by introducing a novel boundary-sensitive pretext (BSP) task. Instead of relying on costly manual annotations of temporal boundaries, we propose to synthesize temporal boundaries in existing video action classification datasets. By defining different ways of synthesizing boundaries, BSP can then be simply conducted in a self-supervised manner via the classification of the boundary types. This enables the learning of video representations that are much more transferable to downstream temporal localization tasks. Extensive experiments show that the proposed BSP is superior and complementary to the existing action classification-based pre-training counterpart, and achieves new state-of-the-art performance on several temporal localization tasks. Please visit our website for more details https://frostinassiky.github.io/bsp.

Vision transformers (ViTs) have pushed the state-of-the-art for various visual recognition tasks by patch-wise image tokenization followed by self-attention. However, the employment of self-attention modules results in a quadratic complexity in both computation and memory usage. Various attempts on approximating the self-attention computation with linear complexity have been made in Natural Language Processing. However, an in-depth analysis in this work shows that they are either theoretically flawed or empirically ineffective for visual recognition. We further identify that their limitations are rooted in keeping the softmax self-attention during approximations. Specifically, conventional self-attention is computed by normalizing the scaled dot-product between token feature vectors. Keeping this softmax operation challenges any subsequent linearization efforts. Based on this insight, for the first time, a softmax-free transformer or SOFT is proposed. To remove softmax in self-attention, Gaussian kernel function is used to replace the dot-product similarity without further normalization. This enables a full self-attention matrix to be approximated via a low-rank matrix decomposition. The robustness of the approximation is achieved by calculating its Moore-Penrose inverse using a Newton-Raphson method. Extensive experiments on ImageNet show that our SOFT significantly improves the computational efficiency of existing ViT variants. Crucially, with a linear complexity, much longer token sequences are permitted in SOFT, resulting in superior trade-off between accuracy and complexity.

Most existing temporal action localization (TAL) methods rely on a transfer learning pipeline: by first optimizing a video encoder on a large action classification dataset (i.e., source domain), followed by freezing the encoder and training a TAL head on the action localization dataset (i.e., target domain). This results in a task discrepancy problem for the video encoder – trained for action classification, but used for TAL. Intuitively, joint optimization with both the video encoder and TAL head is a strong baseline solution to this discrepancy. However, this is not operable for TAL subject to the GPU memory constraints, due to the prohibitive computational cost in processing long untrimmed videos. In this paper, we resolve this challenge by introducing a novel low-fidelity (LoFi) video encoder optimization method. Instead of always using the full training configurations in TAL learning, we propose to reduce the mini-batch composition in terms of temporal, spatial, or spatio-temporal resolution so that jointly optimizing the video encoder and TAL head becomes operable under the same memory conditions of a mid-range hardware budget. Crucially, this enables the gradients to flow backwards through the video encoder conditioned on a TAL supervision loss, favourably solving the task discrepancy problem and providing more effective feature representations. Extensive experiments show that the proposed LoFi optimization approach can significantly enhance the performance of existing TAL methods. Encouragingly, even with a lightweight ResNet18 based video encoder in a single RGB stream, our method surpasses two-stream (RGB + optical-flow) ResNet50 based alternatives, often by a good margin. Our code is publicly available at https://github.com/saic-fi/lofiactionlocalization.

Existing logo detection methods mostly rely on supervised learning with a large quantity of labelled training data in limited classes. This restricts their scalability to a large number of logo classes subject to limited labelling budget. In this work, we consider a more scalable open logo detection problem where only a fraction of logo classes are fully labelled whilst the remaining classes are only annotated with a clean icon image (e.g. 1-shot icon supervised). To generalise and transfer knowledge of fully supervised logo classes to other 1-shot icon supervised classes, we propose a Multi-Perspective Cross-Class (MPCC) domain adaptation method. In a data augmentation principle, MPCC conducts feature distribution alignment in two perspectives. Specifically, we align the feature distribution between synthetic logo images of 1-shot icon supervised classes and genuine logo images of fully supervised classes, and that between logo images and non-logo images, concurrently. This allows for mitigating the domain shift problem between model training and testing on 1-shot icon supervised logo classes, simultaneously reducing the model overfitting towards fully labelled logo classes. Extensive comparative experiments show the advantage of MPCC over existing state-of-the-art competitors on the challenging QMUL-OpenLogo benchmark (Su et al., 2018).

Abstract Existing person re-identification (re-id) methods mostly exploit a large set of cross-camera identity labelled training data. This requires a tedious data collection and annotation process, leading to poor scalability in practical re-id applications. On the other hand unsupervised re-id methods do not need identity label information, but they usually suffer from much inferior and insufficient model performance. To overcome these fundamental limitations, we propose a novel person re-identification paradigm based on an idea ofindependentper-camera identity annotation. This eliminates the most time-consuming and tedious inter-camera identity labelling process, significantly reducing the amount of human annotation efforts. Consequently, it gives rise to a more scalable and more feasible setting, which we callIntra-Camera Supervised (ICS)person re-id, for which we formulate a Multi-tAsk mulTi-labEl (MATE) deep learning method. Specifically, MATE is designed for self-discovering the cross-camera identity correspondence in a per-camera multi-task inference framework. Extensive experiments demonstrate the cost-effectiveness superiority of our method over the alternative approaches on three large person re-id datasets. For example, MATE yields 88.7% rank-1 score on Market-1501 in the proposed ICS person re-id setting, significantly outperforming unsupervised learning models and closely approaching conventional fully supervised learning competitors.

This work introduces a novel data augmentation method for few-shot website fingerprinting (WF) attack where only a handful of training samples per website are available for deep learning model optimization. Moving beyond earlier WF methods relying on manually-engineered feature representations, more advanced deep learning alternatives demonstrate that learning feature representations automatically from training data is superior. Nonetheless, this advantage is subject to an unrealistic assumption that there exist many training samples per website, which otherwise will disappear. To address this, we introduce a model-agnostic, efficient, and harmonious data augmentation (HDA) method that can improve deep WF attacking methods significantly. HDA involves both intrasample and intersample data transformations that can be used in a harmonious manner to expand a tiny training dataset to an arbitrarily large collection, therefore effectively and explicitly addressing the intrinsic data scarcity problem. We conducted expensive experiments to validate our HDA for boosting state-of-the-art deep learning WF attack models in both closed-world and open-world attacking scenarios, at absence and presence of strong defense. For instance, in the more challenging and realistic evaluation scenario with WTF-PAD-based defense, our HDA method surpasses the previous state-of-the-art results by nearly 3% in classification accuracy in the 20-shot learning case. An earlier version of this work Chen et al. (2021) has been presented as preprint in ArXiv (https://arxiv.org/abs/2101.10063).

Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation. However, convolutional neural networks (CNNs) are inherently limited to model such dependencies due to the naive structure in its building modules (e.g., local convolution kernel). While recent global aggregation methods are beneficial for long-range structure information modelling, they would oversmooth and bring noise to the regions contain fine details (e.g., boundaries and small objects), which are very much cared in the semantic segmentation task. To alleviate this problem, we propose to explore the local context for making the aggregated long-range relationship being distributed more accurately in local regions. In particular, we design a novel local distribution module which models the affinity map between global and local relationship for each pixel adaptively. Integrating existing global aggregation modules, we show that our approach can be modularized as an end-to-end trainable block and easily plugged into existing semantic segmentation networks, giving rise to the GALD networks. Despite its simplicity and versatility, our approach allows us to build new state of the art on major semantic segmentation benchmarks including Cityscapes, ADE20K, Pascal Context, Camvid and COCO-stuff. Code and trained models are released at https://github.com/lxtGH/GALD-DGCNet to foster further research.

Semi-supervised learning (SSL) aims to avoid the need for collecting prohibitively expensive labelled training data. Whilst demonstrating impressive performance boost, existing SSL methods artificially assume that small labelled data and large unlabelled data are drawn from the same class distribution. In a more realistic scenario with class distribution mismatch between the two sets, they often suffer severe performance degradation due to error propagation introduced by irrelevant unlabelled samples. Our work addresses this under-studied and realistic SSL problem by a novel algorithm named Uncertainty-Aware Self-Distillation (UASD). Specifically, UASD produces soft targets that avoid catastrophic error propagation, and empower learning effectively from unconstrained unlabelled data with out-of-distribution (OOD) samples. This is based on joint Self-Distillation and OOD filtering in a unified formulation. Without bells and whistles, UASD significantly outperforms six state-of-the-art methods in more realistic SSL under class distribution mismatch on three popular image classification datasets: CIFAR10, CIFAR100, and TinyImageNet.

Convolutional neural networks (CNNs) have achieved unprecedented success in a variety of computer vision tasks. However, they usually rely on supervised model learning with the need for massive labelled training data, limiting dramatically their usability and deployability in real-world scenarios without any labelling budget. In this work, we introduce a general-purpose unsupervised deep learning approach to deriving discriminative feature representations. It is based on self-discovering semantically consistent groups of unlabelled training samples with the same class concepts through a progressive affinity diffusion process. Extensive experiments on object image classification and clustering show the performance superiority of the proposed method over the state-of-the-art unsupervised learning models using six common image recognition benchmarks including MNIST, SVHN, STL10, CIFAR10, CIFAR100 and ImageNet.

Existing neural architecture search (NAS) methods often operate in discrete or continuous spaces directly, which ignores the graphical topology knowledge of neural networks. This leads to suboptimal search performance and efficiency, given the factor that neural networks are essentially directed acyclic graphs (DAG). In this work, we address this limitation by introducing a novel idea of neural graph embedding (NGE). Specifically, we represent the building block (i.e. the cell) of neural networks with a neural DAG, and learn it by leveraging a Graph Convolutional Network to propagate and model the intrinsic topology information of network architectures. This results in a generic neural network representation integrable with different existing NAS frameworks. Extensive experiments show the superiority of NGE over the state-of-the-art methods on image classification and semantic segmentation.

Existing unsupervised person re-identification (re-id) methods mainly focus on cross-domain adaptation or one-shot learning. Although they are more scalable than the supervised learning counterparts, relying on a relevant labelled source domain or one labelled tracklet per person initialisation still restricts their scalability in real-world deployments. To alleviate these problems, some recent studies develop unsupervised tracklet association and bottom-up image clustering methods, but they still rely on explicit camera annotation or merely utilise suboptimal global clustering. In this work, we formulate a novel tracklet self-supervised learning (TSSL) method, which is capable of capitalising directly from abundant unlabelled tracklet data, to optimise a feature embedding space for both video and image unsupervised re-id. This is achieved by designing a comprehensive unsupervised learning objective that accounts for tracklet frame coherence, tracklet neighbourhood compactness, and tracklet cluster structure in a unified formulation. As a pure unsupervised learning re-id model, TSSL is end-to-end trainable at the absence of source data annotation, person identity labels, and camera prior knowledge. Extensive experiments demonstrate the superiority of TSSL over a wide variety of the state-of-the-art alternative methods on four large-scale person re-id benchmarks, including Market-1501, DukeMTMC-ReID, MARS and DukeMTMC-VideoReID.

Person images captured by unconstrained surveillance cameras often have low resolutions (LR). This causes the resolution mismatch problem when matched against the high-resolution (HR) gallery images, negatively affecting the performance of person re-identification (re-id). An effective approach is to leverage image super-resolution (SR) along with person re-id in a joint learning manner. However, this scheme is limited due to dramatically more difficult gradients backpropagation during training. In this paper, we introduce a novel model training regularisation method, called Inter-Task Association Critic (INTACT), to address this fundamental problem. Specifically, INTACT discovers the underlying association knowledge between image SR and person re-id, and leverages it as an extra learning constraint for enhancing the compatibility of SR model with person re-id in HR image space. This is realised by parameterising the association constraint which enables it to be automatically learned from the training data. Extensive experiments validate the superiority of INTACT over the state-of-the-art approaches on the cross-resolution re-id task using five standard person re-id datasets.

By simultaneously learning visual features and data grouping, deep clustering has shown impressive ability to deal with unsupervised learning for structure analysis of high-dimensional visual data. Existing deep clustering methods typically rely on local learning constraints based on inter-sample relations and/or self-estimated pseudo labels. This is susceptible to the inevitable errors distributed in the neighbourhoods and suffers from error-propagation during training. In this work, we propose to solve this problem by learning the most confident clustering solution from all the possible separations, based on the observation that assigning samples from the same semantic categories into different clusters will reduce both the intra-cluster compactness and inter-cluster diversity, i.e. lower partition confidence. Specifically, we introduce a novel deep clustering method named PartItion Confidence mAximisation (PICA). It is established on the idea of learning the most semantically plausible data separation, in which all clusters can be mapped to the ground-truth classes one-to-one, by maximising the "global" partition confidence of clustering solution. This is realised by introducing a differentiable partition uncertainty index and its stochastic approximation as well as a principled objective loss function that minimises such index, all of which together enables a direct adoption of the conventional deep networks and mini-batch based model training. Extensive experiments on six widely-adopted clustering benchmarks demonstrate our model's performance superiority over a wide range of the state-of-the-art approaches. The code is available online.

A common strategy adopted by existing state-of-the-art unsupervised domain adaptation (UDA) methods is to employ two classifiers to identify the misaligned local regions between source and target domain. Following the 'wisdom of the crowd' principle, one has to ask: why stop at two? Indeed, we find that using more classifiers leads to better performance, but also introduces more model parameters, therefore risking overfitting. In this paper, we introduce a novel method called STochastic clAssifieRs (STAR) for addressing this problem. Instead of representing one classifier as a weight vector, STAR models it as a Gaussian distribution with its variance representing the inter-classifier discrepancy. With STAR, we can now sample an arbitrary number of classifiers from the distribution, whilst keeping the model size the same as having two classifiers. Extensive experiments demonstrate that a variety of existing UDA methods can greatly benefit from STAR and achieve the state-of-the-art performance on both image classification and semantic segmentation tasks.

Existing object detection methods typically rely on the availability of abundant labelled training samples per class and offline model training in a batch mode. These requirements substantially limit their scalability to open-ended accommodation of novel classes with limited labelled training data, both in terms of model accuracy and training efficiency during deployment. We present the first study aiming to go beyond these limitations by considering the Incremental Few-Shot Detection (iFSD) problem setting, where new classes must be registered incrementally (without revisiting base classes) and with few examples. To this end we propose OpeN-ended Centre nEt (ONCE), a detector designed for incrementally learning to detect novel class objects with few examples. This is achieved by an elegant adaptation of the efficient CentreNet detector to the few-shot learning scenario, and meta-learning a class-wise code generator model for registering novel classes. ONCE fully respects the incremental learning paradigm, with novel class registration requiring only a single forward pass of few-shot training samples, and no access to base classes - thus making it suitable for deployment on embedded devices, etc. Extensive experiments conducted on both the standard object detection (COCO, PASCAL VOC) and fashion landmark detection (DeepFashion2) tasks show the feasibility of iFSD for the first time, opening an interesting and very important line of research.

While being the de facto standard coordinate representation for human pose estimation, heatmap has not been investigated in-depth. This work fills this gap. For the first time, we find that the process of decoding the predicted heatmaps into the final joint coordinates in the original image space is surprisingly significant for the performance. We further probe the design limitations of the standard coordinate decoding method, and propose a more principled distributionaware decoding method. Also, we improve the standard coordinate encoding process (i.e. transforming ground-truth coordinates to heatmaps) by generating unbiased/accurate heatmaps. Taking the two together, we formulate a novel Distribution-Aware coordinate Representation of Keypoints (DARK) method. Serving as a model-agnostic plug-in, DARK brings about significant performance boost to existing human pose estimation models. Extensive experiments show that DARK yields the best results on two common benchmarks, MPII and COCO. Besides, DARK achieves the 2nd place entry in the ICCV 2019 COCO Keypoints Challenge. The code is available online.

Existing facial image super-resolution (SR) methods focus mostly on improving "artificially down-sampled" lowresolution (LR) imagery. Such SR models, although strong at handling artificial LR images, often suffer from significant performance drop on genuine LR test data. Previous unsupervised domain adaptation (UDA) methods address this issue by training a model using unpaired genuine LR and HR data as well as cycle consistency loss formulation. However, this renders the model overstretched with two tasks: consistifying the visual characteristics and enhancing the image resolution. Importantly, this makes the end-to-end model training ineffective due to the difficulty of back-propagating gradients through two concatenated CNNs. To solve this problem, we formulate a method that joins the advantages of conventional SR and UDA models. Specifically, we separate and control the optimisations for characteristics consistifying and image super-resolving by introducing Characteristic Regularisation (CR) between them. This task split makes the model training more effective and computationally tractable. Extensive evaluations demonstrate the performance superiority of our method over state-of-the-art SR and UDA models on both genuine and artificial LR facial imagery data.

Abstract Existing person re-identification (re-id) deep learning methods rely heavily on the utilisation of large and computationally expensive convolutional neural networks. They are thereforenot scalableto large scale re-id deployment scenarios with the need of processing a large amount of surveillance video data, due to the lengthy inference process with high computing costs. In this work, we address this limitation via jointly learning re-id attention selection. Specifically, we formulate a novelharmonious attention network(HAN) framework to jointly learn soft pixel attention and hard region attention alongside simultaneous deep feature representation learning, particularly enabling more discriminative re-id matching byefficientnetworks with more scalable model inference and feature matching. Extensive evaluations validate the cost-effectiveness superiority of the proposed HAN approach for person re-id against a wide variety of state-of-the-art methods on four large benchmark datasets: CUHK03, Market-1501, DukeMTMC, and MSMT17.

Most existing person re-identification (re-id) methods rely on supervised model learning on per-camera-pair manually labelled pairwise training data. This leads to poor scalability in a practical re-id deployment, due to the lack of exhaustive identity labelling of positive and negative image pairs for every camera-pair. In this work, we present an unsupervised re-id deep learning approach. It is capable of incrementally discovering and exploiting the underlying re-id discriminative information from automatically generated person tracklet data end-to-end. We formulate an Unsupervised Tracklet Association Learning (UTAL) framework. This is by jointly learning within-camera tracklet discrimination and cross-camera tracklet association in order to maximise the discovery of tracklet identity matching both within and across camera views. Extensive experiments demonstrate the superiority of the proposed model over the state-of-the-art unsupervised learning and domain adaptation person re-id methods on eight benchmarking datasets.

The objective learning formulation is essential for the success of convolutional neural networks. In this work, we analyse thoroughly the standard learning objective functions for multiclass classification CNNs: softmax regression (SR) for singlelabel scenario and logistic regression (LR) for multi-label scenario. Our analyses lead to an inspiration of exploiting LR for single-label classification learning, and then the disclosing of the negative class distraction problem in LR. To address this problem, we develop two novel LR based objective functions that not only generalise the conventional LR but importantly turn out to be competitive alternatives to SR in single label classification. Extensive comparative evaluations demonstrate the model learning advantages of the proposed LR functions over the commonly adopted SR in single-label coarse-grained object categorisation and cross-class fine-grained person instance identification tasks. We also show the performance superiority of our method on clothing attribute classification in comparison to the vanilla LR function. The code had been made publicly available.

Existing human pose estimation approaches often only consider how to improve the model generalisation performance, but putting aside the significant efficiency problem. This leads to the development of heavy models with poor scalability and cost-effectiveness in practical use. In this work, we investigate the under-studied but practically critical pose model efficiency problem. To this end, we present a new Fast Pose Distillation (FPD) model learning strategy. Specifically, the FPD trains a lightweight pose neural network architecture capable of executing rapidly with low computational cost. It is achieved by effectively transferring the pose structure knowledge of a strong teacher network. Extensive evaluations demonstrate the advantages of our FPD method over a broad range of state-of-the-art pose estimation approaches in terms of model cost-effectiveness on two standard benchmark datasets, MPII Human Pose and Leeds Sports Pose.

Existing person search methods predominantly assume the availability of at least one-shot imagery sample of the queried person. This assumption is limited in circumstances where only a brief textual (or verbal) description of the target person is available. In this work, we present a deep learning method for attribute text description based person search without any query imagery. Whilst conventional cross-modality matching methods, such as global visual-textual embedding based zero-shot learning and local individual attribute recognition, are functionally applicable, they are limited by several assumptions invalid to person search in deployment scale, data quality, and/or category name semantics. We overcome these issues by formulating an Attribute-Image Hierarchical Matching (AIHM) model. It is able to more reliably match text attribute descriptions with noisy surveillance person images by jointly learning global category-level and local attribute-level textual-visual embedding as well as matching. Extensive evaluations demonstrate the superiority of our AIHM model over a wide variety of state-of-the-art methods on three publicly available attribute labelled surveillance person search benchmarks: Market-1501, DukeMTMC, and PA100K.

Existing person re-identification (re-id) methods mostly assume the availability of large-scale identity labels for model learning in any target domain deployment. This greatly limits their scalability in practice. To tackle this limitation, we propose a novel Instance-Guided Context Rendering scheme, which transfers the source person identities into diverse target domain contexts to enable supervised re-id model learning in the unlabelled target domain. Unlike previous image synthesis methods that transform the source person images into limited fixed target styles, our approach produces more visually plausible, and diverse synthetic training data. Specifically, we formulate a dual conditional generative adversarial network that augments each source person image with rich contextual variations. To explicitly achieve diverse rendering effects, we leverage abundant unlabelled target instances as contextual guidance for image generation. Extensive experiments on Market-1501, DukeMTMC-reID and CUHK03 benchmarks show that the re-id performance can be significantly improved when using our synthetic data in cross-domain re-id model learning.

Existing deep learning algorithms for person re-identification (re-id) typically rely on single-sample classification or pairwise matching constraints. This indicates a breach of deployment due to ignoring the probe-specific matching information against the gallery set encoded in ranking lists. In this work, we address this problem by exploring the idea of RANkinG Ensembles (RANGE) that learns such information from the ranking lists. Specifically, given an off-the-self deep re-id feature representation model, we construct per-probe ranking lists and exploit them to learn inter ranking ensemble representation. To mitigate the harm of inevitable false gallery positives, we further introduce a complementary intra ranking ensemble representation. Extensive experiments show that both supervised and unsupervised re-id benefit from the proposed RANGE method on four challenging benchmarks: MSMT17, Market-1501, DukeMTMC-ReID, and CUHK03.

Deep convolutional neural networks (CNNs) have demonstrated remarkable success in computer vision by supervisedly learning strong visual feature representations. However, training CNNs relies heavily on the availability of exhaustive training data annotations, limiting significantly their deployment and scalability in many application scenarios. In this work, we introduce a generic unsupervised deep learning approach to training deep models without the need for any manual label supervision. Specifically, we progressively discover sample anchored/centred neighbourhoods to reason and learn the underlying class decision boundaries iteratively and accumulatively. Every single neighbourhood is specially formulated so that all the member samples can share the same unseen class labels at high probability for facilitating the extraction of class discriminative feature representations during training. Experiments on image classification show the performance advantages of the proposed method over the state-of-the-art unsupervised learning models on six benchmarks including both coarse-grained and fine-grained object image categorisation.

Model learning from class imbalanced training data is a long-standing and significant challenge for machine learning. In particular, existing deep learning methods consider mostly either class balanced data or moderately imbalanced data in model training, and ignore the challenge of learning from significantly imbalanced training data. To address this problem, we formulate a class imbalanced deep learning model based on batch-wise incremental minority (sparsely sampled) class rectification by hard sample mining in majority (frequently sampled) classes during model training. This model is designed to minimise the dominant effect of majority classes by discovering sparsely sampled boundaries of minority classes in an iterative batch-wise learning process. To that end, we introduce a Class Rectification Loss (CRL) function that can be deployed readily in deep network architectures. Extensive experimental evaluations are conducted on three imbalanced person attribute benchmark datasets (CelebA, X-Domain, DeepFashion) and one balanced object category benchmark dataset (CIFAR-100). These experimental results demonstrate the performance advantages and model scalability of the proposed batch-wise incremental minority class rectification model over the existing state-of-the-art models for addressing the problem of imbalanced data learning.

Person images captured by public surveillance cameras often have low resolutions (LR) in addition to uncontrolled pose variations, background clutters and occlusions. This gives rise to the resolution mismatch problem when matched against the high resolution (HR) gallery images (typically available in enrolment), which adversely affects the performance of person re-identification (re-id) that aims to associate images of the same person captured at different locations and different time. Most existing re-id methods either ignore this problem or simply upscale LR images. In this work, we address this problem by developing a novel approach called Super-resolution and Identity joiNt learninG (SING) to simultaneously optimise image super-resolution and person re-id matching. This approach is instantiated by designing a hybrid deep Convolutional Neural Network for improving cross-resolution re-id performance. We further introduce an adaptive fusion algorithm for accommodating multi-resolution LR images. Extensive evaluations show the advantages of our method over related state-of-the-art re-id and super-resolution methods on cross-resolution re-id benchmarks.

Existing person re-identification (re-id) methods either assume the availability of well-aligned person bounding box images as model input or rely on constrained attention selection mechanisms to calibrate misaligned images. They are therefore sub-optimal for re-id matching in arbitrarily aligned person images potentially with large human pose variations and unconstrained auto-detection errors. In this work, we show the advantages of jointly learning attention selection and feature representation in a Convolutional Neural Network (CNN) by maximising the complementary information of different levels of visual attention subject to re-id discriminative learning constraints. Specifically, we formulate a novel Harmonious Attention CNN (HA-CNN) model for joint learning of soft pixel attention and hard regional attention along with simultaneous optimisation of feature representations, dedicated to optimise person re-id in uncontrolled (misaligned) images. Extensive comparative evaluations validate the superiority of this new HA-CNN model for person re-id over a wide variety of state-of-the-art methods on three large-scale benchmarks including CUHK03, Market-1501, and DukeMTMC-ReID.

Most existing person re-identification (re-id) methods require supervised model learning from a separate large set of pairwise labelled training data for every single camera pair. This significantly limits their scalability and usability in real-world large scale deployments with the need for performing re-id across many camera views. To address this scalability problem, we develop a novel deep learning method for transferring the labelled information of an existing dataset to a new unseen (unlabelled) target domain for person re-id without any supervised learning in the target domain. Specifically, we introduce an Transferable Joint Attribute-Identity Deep Learning (TJ-AIDL) for simultaneously learning an attribute-semantic and identity-discriminative feature representation space transferrable to any new (unseen) target domain for re-id tasks without the need for collecting new labelled training data from the target domain (i.e. unsupervised learning in the target domain). Extensive comparative evaluations validate the superiority of this new TJ-AIDL model for unsupervised person re-id over a wide range of state-of-the-art methods on four challenging benchmarks including VIPeR, PRID, Market-1501, and DukeMTMC-ReID.

Knowledge distillation is effective to train the small and generalisable network models for meeting the low-memory and fast running requirements. Existing offline distillation methods rely on a strong pre-trained teacher, which enables favourable knowledge discovery and transfer but requires a complex two-phase training procedure. Online counterparts address this limitation at the price of lacking a high-capacity teacher. In this work, we present an On-the-fly Native Ensemble (ONE) learning strategy for one-stage online distillation. Specifically, ONE only trains a single multi-branch network while simultaneously establishing a strong teacher on-the-fly to enhance the learning of target network. Extensive evaluations show that ONE improves the generalisation performance of a variety of deep neural networks more significantly than alternative methods on four image classification dataset: CIFAR10, CIFAR100, SVHN, and ImageNet, whilst having the computational efficiency advantages.

Most existing person re-identification (re-id) methods are unsuitable for real-world deployment due to two reasons: Unscalability to large population size , and Inadaptability over time . In this work, we present a unified solution to address both problems. Specifically, we propose to construct an identity regression space (IRS) based on embedding different training person identities (classes) and formulate re-id as a regression problem solved by identity regression in the IRS. The IRS approach is characterised by a closed-form solution with high learning efficiency and an inherent incremental learning capability with human-in-the-loop. Extensive experiments on four benchmarking datasets (VIPeR, CUHK01, CUHK03 and Market-1501) show that the IRS model not only outperforms state-of-the-art re-id methods, but also is more scalable to large re-id population size by rapidly updating model and actively selecting informative samples with reduced human labelling effort.

The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion. While a large number of distance metric/subspace learning models have been developed for re-id, the cross-view transformations they learned are view-generic and thus potentially less effective in quantifying the feature distortion inherent to each camera view. Learning view-specific feature transformations for re-id (i.e., view-specific re-id), an under-studied approach, becomes an alternative resort for this problem. In this work, we formulate a novel view-specific person re-identification framework from the feature augmentation point of view, called Camera coR relation Aware Feature augmenTation (CRAFT). Specifically, CRAFT performs cross-view adaptation by automatically measuring camera correlation from cross-view visual data distribution and adaptively conducting feature augmentation to transform the original features into a new adaptive space. Through our augmentation framework, view-generic learning algorithms can be readily generalized to learn and optimize view-specific sub-models whilst simultaneously modelling view-generic discrimination information. Therefore, our framework not only inherits the strength of view-generic model learning but also provides an effective way to take into account view specific characteristics. Our CRAFT framework can be extended to jointly learn view-specific feature transformations for person re-id across a large network with more than two cameras, a largely under-investigated but realistic re-id setting. Additionally, we present a domain-generic deep person appearance representation which is designed particularly to be towards view invariant for facilitating cross-view adaptation by CRAFT. We conducted extensively comparative experiments to validate the superiority and advantages of our proposed framework over state-of-the-art competitors on contemporary challenging person re-id datasets.

Existing person re-identification (re-id) methods typically assume that: 1) any probe person is guaranteed to appear in the gallery target population during deployment (i.e., closed-world) and 2) the probe set contains only a limited number of people (i.e., small search scale). Both assumptions are artificial and breached in real-world applications, since the probe population in target people search can be extremely vast in practice due to the ambiguity of probe search space boundary. Therefore, it is unrealistic that any probe person is assumed as one target people, and a large-scale search in person images is inherently demanded. In this paper, we introduce a new person re-id search setting, called large scale open-world (LSOW) re-id, characterized by huge size probe images and open person population in search thus more close to practical deployments. Under LSOW, the under-studied problem of person re-id efficiency is essential in addition to that of commonly studied re-id accuracy. We, therefore, develop a novel fast person re-id method, called Cross-view Identity Correlation and vErification (X-ICE) hashing, for joint learning of cross-view identity representation binarisation and discrimination in a unified manner. Extensive comparative experiments on three large-scale benchmarks have been conducted to validate the superiority and advantages of the proposed X-ICE method over a wide range of the state-of-the-art hashing models, person re-id methods, and their combinations.

Recognising detailed facial or clothing attributes in images of people is a challenging task for computer vision, especially when the training data are both in very large scale and extremely imbalanced among different attribute classes. To address this problem, we formulate a novel scheme for batch incremental hard sample mining of minority attribute classes from imbalanced large scale training data. We develop an end-to-end deep learning framework capable of avoiding the dominant effect of majority classes by discovering sparsely sampled boundaries of minority classes. This is made possible by introducing a Class Rectification Loss (CRL) regularising algorithm. We demonstrate the advantages and scalability of CRL over existing state-of-the-art attribute recognition and imbalanced data learning models on two large scale imbalanced benchmark datasets, the CelebA facial attribute dataset and the X-Domain clothing attribute dataset.

Recognising semantic pedestrian attributes in surveillance images is a challenging task for computer vision, particularly when the imaging quality is poor with complex background clutter and uncontrolled viewing conditions, and the number of labelled training data is small. In this work, we formulate a Joint Recurrent Learning (JRL) model for exploring attribute context and correlation in order to improve attribute recognition given small sized training data with poor quality images. The JRL model learns jointly pedestrian attribute correlations in a pedestrian image and in particular their sequential ordering dependencies (latent high-order correlation) in an end-to-end encoder/ decoder recurrent network. We demonstrate the performance advantage and robustness of the JRL model over a wide range of state-of-the-art deep models for pedestrian attribute recognition, multi-label image classification, and multi-person image annotation on two largest pedestrian attribute benchmarks PETA and RAP.

Existing person re-identification (re-id) methods rely mostly on either localised or global feature representation. This ignores their joint benefit and mutual complementary effects. In this work, we show the advantages of jointly learning local and global features in a Convolutional Neural Network (CNN) by aiming to discover correlated local and global features in different context. Specifically, we formulate a method for joint learning of local and global feature selection losses designed to optimise person re-id when using generic matching metrics such as the L2 distance. We design a novel CNN architecture for Jointly Learning Multi-Loss (JLML) of local and global discriminative feature optimisation subject concurrently to the same re-id labelled information. Extensive comparative evaluations demonstrate the advantages of this new JLML model for person re-id over a wide range of state-of-the-art re-id methods on five benchmarks (VIPeR, GRID, CUHK01, CUHK03, Market-1501).

Recognising detailed clothing characteristics (finegrained attributes) in unconstrained images of people inthe-wild is a challenging task for computer vision, especially when there is only limited training data from the wild whilst most data available for model learning are captured in well-controlled environments using fashion models (well lit, no background clutter, frontal view, high-resolution). In this work, we develop a deep learning framework capable of model transfer learning from well-controlled shop clothing images collected from web retailers to in-the-wild images from the street. Specifically, we formulate a novel Multi-Task Curriculum Transfer (MTCT) deep learning method to explore multiple sources of different types of web annotations with multi-labelled fine-grained attributes. Our multi-task loss function is designed to extract more discriminative representations in training by jointly learning all attributes, and our curriculum strategy exploits the staged easy-to-hard transfer learning motivated by cognitive studies. We demonstrate the advantages of the MTCT model over the state-of-the-art methods on the X-Domain benchmark, a large scale clothing attribute dataset. Moreover, we show that the MTCT model has a notable advantage over contemporary models when the training data size is small.

Logo detection in unconstrained images is challenging, particularly when only very sparse labelled training images are accessible due to high labelling costs. In this work, we describe a model training image synthesising method capable of improving significantly logo detection performance when only a handful of (e.g., 10) labelled training images captured in realistic context are available, avoiding extensive manual labelling costs. Specifically, we design a novel algorithm for generating Synthetic Context Logo (SCL) training images to increase model robustness against unknown background clutters, resulting in superior logo detection performance. For benchmarking model performance, we introduce a new logo detection dataset TopLogo-10 collected from top 10 most popular clothing/wearable brandname logos captured in rich visual context. Extensive comparisons show the advantages of our proposed SCL model over the state-of-the-art alternatives for logo detection using two real-world logo benchmark datasets: FlickrLogo-32 and our new TopLogo-101.

Clustering tagged videos into semantic groups is importantbut challenging due to the need for jointly learning correlations between heterogeneous visual and tag data. The taskis made more difficult by inherently sparse and incompletetag labels. In this work, we develop a method for accuratelyclustering tagged videos based on a novel Hierarchical-MultiLabel Random Forest model capable of correlating structured visual and tag information. Specifically, our model exploits hierarchically structured tags of different abstractnessof semantics and multiple tag statistical correlations, thus discovers more accurate semantic correlations among differentvideo data, even with highly sparse/incomplete tags.

Most existing person re-identification (ReID) methods assume the availability of extensively labelled cross-view person pairs and a closed-set scenario (i.e. all the probe people exist in the gallery set). These two assumptions significantly limit their usefulness and scalability in real-world applications, particularly with large scale camera networks. To overcome the limitations, we introduce a more challenging yet realistic ReID setting termed OneShot-OpenSet-RelD, and propose a novel Regularised Kernel Subspace Learning model for ReID under this setting. Our model differs significantly from existing ReID methods due to its ability of effectively learning cross-view identity-specific information from unlabelled data alone, and its flexibility of naturally accommodating pairwise labels if available.

Current person re-identification (ReID) methods typically rely on single-frame imagery features, whilst ignoring space-time information from image sequences often available in the practical surveillance scenarios. Single-frame (single-shot) based visual appearance matching is inherently limited for person ReID in public spaces due to the challenging visual ambiguity and uncertainty arising from non-overlapping camera views where viewing condition changes can cause significant people appearance variations. In this work, we present a novel model to automatically select the most discriminative video fragments from noisy/incomplete image sequences of people from which reliable space-time and appearance features can be computed, whilst simultaneously learning a video ranking function for person ReID. Using the PRID 2011, iLIDS-VID, and HDA+ image sequence datasets, we extensively conducted comparative evaluations to demonstrate the advantages of the proposed model over contemporary gait recognition, holistic image sequence matching and state-of-the-art single-/multi-shot ReID methods.

While clustering is usually an unsupervised operation, there are circumstances where we have access to prior belief that pairs of samples should (or should not) be assigned with the same cluster. Constrained clustering aims to exploit this prior belief as constraint (or weak supervision) to influence the cluster formation so as to obtain a data structure more closely resembling human perception. Two important issues remain open: 1) how to exploit sparse constraints effectively and 2) how to handle ill-conditioned/noisy constraints generated by imperfect oracles. In this paper, we present a novel pairwise similarity measure framework to address the above issues. Specifically, in contrast to existing constrained clustering approaches that blindly rely on all features for constraint propagation, our approach searches for neighborhoods driven by discriminative feature selection for more effective constraint diffusion. Crucially, we formulate a novel approach to handling the noisy constraint problem, which has been unrealistically ignored in the constrained clustering literature. Extensive comparative results show that our method is superior to the state-of-the-art constrained clustering approaches and can generally benefit existing pairwise similarity-based data clustering algorithms, such as spectral clustering and affinity propagation.

Spectral clustering requires robust and meaningful affinity graphs as input in order to form clusters with desired structures that can well support human intuition. To construct such affinity graphs is non-trivial due to the ambiguity and uncertainty inherent in the raw data. In contrast to most existing clustering methods that typically employ all available features to construct affinity matrices with the Euclidean distance, which is often not an accurate representation of the underlying data structures, we propose a novel unsupervised approach to generating more robust affinity graphs via identifying and exploiting discriminative features for improving spectral clustering. Specifically, our model is capable of capturing and combining subtle similarity information distributed over discriminative feature subspaces for more accurately revealing the latent data distribution and thereby leading to improved data clustering, especially with heterogeneous data sources. We demonstrate the efficacy of the proposed approach on challenging image and video datasets.

Generating coherent synopsis for surveillance video stream remains a formidable challenge due to the ambiguity and uncertainty inherent to visual observations. In contrast to existing video synopsis approaches that rely on visual cues alone, we propose a novel multi-source synopsis framework capable of correlating visual data and independent non-visual auxiliary information to better describe and summarise subtle physical events in complex scenes. Specifically, our unsupervised framework is capable of seamlessly uncovering latent correlations among heterogeneous types of data sources, despite the non-trivial heteroscedasticity and dimensionality discrepancy problems. Additionally, the proposed model is robust to partial or missing non-visual information. We demonstrate the effectiveness of our framework on two crowded public surveillance datasets.

While spectral clustering is usually an unsupervised operation, there are circumstances in which we have prior belief that pairs of samples should (or should not) be assigned with the same cluster. Constrained spectral clustering aims to exploit this prior belief as constraint (or weak supervision) to influence the cluster formation so as to obtain a structure more closely resembling human perception. Two important issues remain open: (1) how to propagate sparse constraints effectively, (2) how to handle ill-conditioned/noisy constraints generated by imperfect oracles. In this paper we present a unified framework to address the above issues. Specifically, in contrast to existing constrained spectral clustering approaches that blindly rely on all features for constructing the spectral, our approach searches for neighbours driven by discriminative feature selection for more effective constraint diffusion. Crucially, we formulate a novel data-driven filtering approach to handle the noisy constraint problem, which has been unrealistically ignored in constrained spectral clustering literature.

Problem: This work systematically investigates the effectiveness of various visual feature coding schemes for facilitating the learning of timedelayed dependencies among disjoint multi-camera views. Related work: Quite a few studies [3, 4, 6] have been proposed to model inter-camera dependency across non-overlapping camera views. Learning time-delayed correlations among disjoint cameras in crowded public scenarios is a non-trivial task: (1) the time gaps between camera views are unknown therefore activities in two related views may occur at arbitrary time delays with high uncertainty; (2) the features are inevitably noisy, ambiguous, and may vary drastically across views owning to illumination condition, camera angles, and changes in object pose. Most state-ofthe-art methods typically hand pick a few features tailored to the target environment, with the hope that those chosen features contain robust and sufficient statistics for correlating the time-delayed activity patterns across disjoint views. These manual approaches to hard selection of features are neither principled nor generalisable to different scene context. Our solution: In this study, we wish to examine the concept that visual features should be coded and selected automatically for robust and accurate time-delayed dependency learning. The contributions of this study are two-fold: (1) We present a systematic study and evaluation to investigate the effectiveness of supervised and unsupervised feature coding methods to facilitate the learning of inter-camera activity pattern dependencies. (2) We systematically evaluate the sensitivity of inter-camera time delayed dependency learning given different training video sizes and region decomposition qualities. These factors are critical for accurate dependency learning but have been largely ignored by the published existing work in the literature. Approach overview: We employ the Random Forest [2] as the supervised feature coding approach. In particular, given a set of localised features extracted from a region, together with people count training label over time, we first train a regression forest to learn the non-linear mapping between the crowd density and the corresponding low-level features. Given unseen data, we then construct a time series based on the predicted crowd density ŷ obtained from the regression forest (RF pred), the treestructured code (tree code) [5], or the combination of the two. As for unsupervised coding scheme, we use the Latent Dirichlet Allocation (LDA) [1] to map the low-level features into codewords that capture the topic distribution, whereby an image region patch (document) d is treated as a collection of j = 1 . . .Ni features (words). To form the unsupervised feature codes, given a sequence of localised feature vectors detected from a region, we first perform quantisation on each feature to generate a bag-of-word representation for all image patches. Similar to text documents, these bag-of-word represented image patches are fed into the LDA, which gives us a topic-based representation. Once having the topic-based code (topic code), we perform k-means quantisation on them, producing the final compact topic-based code, and concatenate them over time to form a time series. To solve the problem of using the feature codes for learning intercamera dependencies, we adopt the Time Delayed Mutual Information (TDMI) proposed in [3] due to its reported effectiveness and simplicity. The input to TDMI are time series generated from either the supervised or the unsupervised coding scheme. In addition to measuring deviation error in transition time, we propose a new metrics to evaluate the effectiveness of different coding methods, called Mutual Information Margin (MIM):