Prompt tuning, a recently emerging paradigm, adapts vision-language pre-trained models to new tasks efficiently by learning "soft prompts" for frozen models. However, in few-shot scenarios, its effectiveness is limited by sensitivity to the initialization and the time-consuming search for optimal initialization, hindering rapid adaptation. Additionally, prompt tuning risks reducing the models' generalizability due to overfitting on scarce training samples. To overcome these challenges, we introduce a novel Gradient-RegulAted Meta-prompt learning (GRAM) framework that jointly meta-learns an efficient soft prompt initialization for better adaptation and a lightweight gradient regulating function for strong cross-domain generalizability in a meta-learning paradigm using only the weakly labeled image-text pre-training data. This is achieved through a Cross-Modal Hierarchical Clustering algorithm that organizes extensive image-text data into a structured hierarchy, facilitating robust meta-learning across diverse domains. Rather than designing a specific prompt tuning method, our GRAM can be easily incorporated into various prompt tuning methods in a model-agnostic way and bring about consistent improvement for them. Further, we consider a more practical but challenging setting: test-time prompt tuning with only unlabeled test samples and propose an improved structure-induced gradient regulating function to leverage the structured semantics of the meta-learning data for zero-shot generalization. This novel approach exploits the hierarchically clustered meta-learning data to model relationships between test-time data and meta-learning prototypes, facilitating the transfer of invariant knowledge without explicit annotations. Meanwhile, we introduce a structure complexity-informed strategy for adaptively constructing meta-training tasks and generating prototypes, which fully considers the diverse semantics within hierarchical clusters of different complexities. Comprehensive experiments demonstrate the state-of-the-art few- and zero-shot generalizability of our method.

The recent Segment Anything Model (SAM) has emerged as a new paradigmatic vision foundation model, showcasing potent zero-shot generalization and flexible prompting. Despite SAM finding applications and adaptations in various domains, its primary limitation lies in the inability to grasp object semantics. In this paper, we present Sambor to seamlessly integrate SAM with the open-vocabulary object detector in an end-to-end framework. While retaining all the remarkable capabilities inherent to SAM, we boost it to detect arbitrary objects from human inputs like category names or reference expressions. Building upon the SAM image encoder, we introduce a novel SideFormer module designed to acquire SAM features adept at perceiving objects and inject comprehensive semantic information for recognition. In addition, we devise an Open-set RPN that leverages SAM proposals to assist in finding potential objects. Consequently, Sambor enables the open-vocabulary detector to equally focus on generalizing both localization and classification sub-tasks. Our approach demonstrates superior zero-shot performance across benchmarks, including COCO and LVIS, proving highly competitive against previous state-of-the-art methods. We aspire for this work to serve as a meaningful endeavor in endowing SAM to recognize diverse object categories and advancing open-vocabulary learning with the support of vision foundation models.

Multimodal pre-trained models like CLIP need large image-text pairs for training but often struggle with domain-specific tasks. Since retraining with specialized and historical data incurs significant memory and time costs, it is important to continually learn new domains in the open world while preserving original performance. However, current continual learning research mainly focuses on single-modal scenarios, and the evaluation criteria are insufficient without considering image-text matching performance and the forgetting of zero-shot performance. This work introduces image-caption datasets from various domains and establishes a multimodal vision-language continual learning benchmark. Then, a novel framework named C-CLIP is proposed, which not only prevents forgetting but also enhances new task learning impressively. Comprehensive experiments demonstrate that our method has strong continual learning ability across different domain image-text datasets, and has little forgetting of the original capabilities of zero-shot prediction, significantly outperforming existing methods.

Traditional approaches to adapting multi-modal large language models (MLLMs) to new tasks have relied heavily on fine-tuning. This paper introduces Efficient Multi-Modal Long Context Learning (EMLoC), a novel training-free alternative that embeds demonstration examples directly into the model input. EMLoC offers a more efficient, flexible, and scalable solution for task adaptation. Because extremely lengthy inputs introduce prohibitive computational and memory overhead, EMLoC contributes a chunk-wise compression mechanism combined with layer-wise adaptive pruning. It condenses long-context multimodal inputs into compact, task-specific memory representations. By adaptively pruning tokens at each layer under a Jensen-Shannon divergence constraint, our method achieves a dramatic reduction in inference complexity without sacrificing performance. This approach is the first to seamlessly integrate compression and pruning techniques for multi-modal long-context learning, offering a scalable and efficient solution for real-world applications. Extensive experiments on diverse vision-language benchmarks demonstrate that EMLoC achieves performance on par with or superior to naive long-context approaches. Our results highlight the potential of EMLoC as a groundbreaking framework for efficient and flexible adaptation of multi-modal models in resource-constrained environments. Codes are publicly available at https://github.com/Zehong-Ma/EMLoC.

Multimodal Large Language Models (MLLMs) are experiencing rapid growth, yielding a plethora of novel works recently. The prevailing trend involves adopting data-driven methodologies, wherein diverse instruction-following datasets were collected. However, these approaches always face the challenge of limited visual perception capabilities, as they solely utilizing CLIP-like encoders to extract visual information from inputs. Though these encoders are pre-trained on billions of image-text pairs, they still grapple with the information loss dilemma, given that textual captions only partially capture the contents depicted in images. To address this limitation, this paper proposes to improve the visual perception ability of MLLMs through a mixture-of-experts knowledge enhancement mechanism. Specifically, this work introduces a novel method that incorporates multi-task encoders and existing visual tools into the MLLMs training and inference pipeline, aiming to provide a more comprehensive summarization of visual inputs. Extensive experiments have evaluated its effectiveness of advancing MLLMs, showcasing improved visual perception capability achieved through the integration of visual experts.

Existing acceleration techniques for video diffusion models often rely on uniform heuristics or time-embedding variants to skip timesteps and reuse cached features. These approaches typically require extensive calibration with curated prompts and risk inconsistent outputs due to prompt-specific overfitting. In this paper, we introduce a novel and robust discovery: a unified magnitude law observed across different models and prompts. Specifically, the magnitude ratio of successive residual outputs decreases monotonically, steadily in most timesteps while rapidly in the last several steps. Leveraging this insight, we introduce a Magnitude-aware Cache (MagCache) that adaptively skips unimportant timesteps using an error modeling mechanism and adaptive caching strategy. Unlike existing methods requiring dozens of curated samples for calibration, MagCache only requires a single sample for calibration. Experimental results show that MagCache achieves 2.10×-2.68× speedups on Open-Sora, CogVideoX, Wan 2.1, and HunyuanVideo, while preserving superior visual fidelity. It significantly outperforms existing methods in LPIPS, SSIM, and PSNR, under similar computational budgets.

The current state-of-the-art text-to-image (T2I) models have found numerous applications, driven by their ability to produce photorealistic images. Concept learning, as one notable application, aims to enable T2I models to generate personalized content and better enable users to create images according to their interests. Nevertheless, the process of concept learning often involves model fine-tuning, which in turn brings the potential risk of overfitting. Such overfitting causes the T2I model to have reduced output diversity and results in poor editability. To mitigate the overfitting problem, we introduce two simple yet effective designs, namely masked textual inversion (MaskTI) and text regularization (TextReg). MaskTI is a variant of vanilla textual inversion that forces the learnable identifier to only attend to the class descriptor. This modification can effectively reduce the overfitting to those uninterested backgrounds. TextReg regulates the fine-tuning of cross-attention modules with simple text prompts without identifiers, which avoids the usage of real images as the regularization prior. Our extensive experiments demonstrate that not only does our approach effectively protect prior knowledge but also has high editability for the personalized model.

Mixture-of-Experts (MoE) models embody the divide-and-conquer concept and are a promising approach for increasing model capacity, demonstrating excellent scalability across multiple domains. In this paper, we integrate the MoE structure into the classic Vision Transformer (ViT), naming it ViMoE, and explore the potential of applying MoE to vision through a comprehensive study on image classification and semantic segmentation. However, we observe that the performance is sensitive to the configuration of MoE layers, making it challenging to obtain optimal results without careful design. The underlying cause is that inappropriate MoE layers lead to unreliable routing and hinder experts from effectively acquiring helpful information. To address this, we introduce a shared expert to learn and capture common knowledge, serving as an effective way to construct a stable ViMoE. Furthermore, we demonstrate how to analyze expert routing behavior, revealing which MoE layers are capable of specializing in handling specific information and which are not. This provides guidance for retaining the critical layers while removing redundancies, thereby advancing ViMoE to be more efficient without sacrificing accuracy. We aspire for this work to offer new insights into the design of vision MoE models and provide valuable empirical guidance for future research.

The challenge of open-vocabulary recognition lies in the model has no clue of new categories it is applied to. Existing works have proposed different methods to embed category cues into the model, e.g., through few-shot fine-tuning, providing category names or textual descriptions to Vision-Language Models. Fine-tuning is time-consuming and degrades the generalization capability. Textual descriptions could be ambiguous and fail to depict visual details. This paper tackles open-vocabulary recognition from a different perspective by referring to multi-modal clues composed of textual descriptions and exemplar images. Our method, named OVMR, adopts two innovative components to pursue a more robust category cues embedding. A multi-modal classifier is first generated by dynamically complementing textual descriptions with image exemplars. A preference-based refinement module is hence applied to fuse uni-modal and multi-modal classifiers, with the aim to alleviate issues of low-quality exemplar images or textual descriptions. The proposed OVMR is a plug-and-play module, and works well with exemplar images randomly crawled from the Internet. Extensive experiments have demonstrated the promising performance of OVMR, e.g., it outperforms existing methods across various scenarios and setups. Codes are publicly available at https://github.com/Zehong-Ma/OVMR.

Text-to-image (T2I) generative models have recently emerged as a powerful tool, enabling the creation of photo-realistic images and giving rise to a multitude of applications. However, the effective integration of T2I models into fundamental image classification tasks remains an open question. A prevalent strategy to bolster image classification performance is through augmenting the training set with synthetic images generated by T2I models. In this study, we scrutinize the shortcomings of both current gener-ative and conventional data augmentation techniques. Our analysis reveals that these methods struggle to produce images that are both faithful (in terms of foreground objects) and diverse (in terms of background contexts) for domain-specific concepts. To tackle this challenge, we introduce an innovative inter-class data augmentation method known as Diff-Mix11https://github.com/Zhicaiwww/Diff-Mix, which enriches the dataset by performing image translations between classes. Our empirical results demonstrate that Diff-Mix achieves a better balance between faith-fulness and diversity, leading to a marked improvement in performance across diverse image classification scenarios, including few-shot, conventional, and long-tail classifications for domain-specific datasets.

Multi-modal Large Language Models (MLLMs) tuned on machine-generated instruction-following data have demonstrated remarkable performance in various multi-modal understanding and generation tasks. However, the hallucinations inherent in machine-generated data, which could lead to hallucinatory outputs in MLLMs, remain under-explored. This work aims to investigate various hallucinations (i.e., object, relation, attribute hallucinations) and mitigate those hallucinatory toxicities in large-scale machine-generated visual instruction datasets. Drawing on the human ability to identify factual errors, we present a novel hallucination detection and elimination framework, HalluciDoctor, based on the cross-checking paradigm. We use our framework to identify and eliminate hallucinations in the training data automatically. Interestingly, HalluciDoctor also indicates that spurious correlations arising from long-tail object cooccurrences contribute to hallucinations. Based on that, we execute counterfactual visual instruction expansion to balance data distribution, thereby enhancing MLLMs' resistance to hallucinations. Comprehensive experiments on hallucination evaluation benchmarks show that our method successfully mitigates 44.6% hallucinations relatively and maintains competitive performance compared to LLaVA. The data and code for this paper are publicly available.11https://github.com/Yuqifan1117/HalluciDoctor

Classifier-free guidance (CFG) is a pivotal technique for balancing the diversity and fidelity of samples in conditional diffusion models. This approach involves utilizing a single model to jointly optimize the conditional score predictor and unconditional score predictor, eliminating the need for additional classifiers. It delivers impressive results and can be employed for continuous and discrete condition representations. However, when the condition is continuous, it prompts the question of whether the trade-off can be further enhanced. Our proposed inner classifier-free guidance (ICFG) provides an alternative perspective on the CFG method when the condition has a specific structure, demonstrating that CFG represents a first-order case of ICFG. Additionally, we offer a second-order implementation, highlighting that even without altering the training policy, our second-order approach can introduce new valuable information and achieve an improved balance between fidelity and diversity for Stable Diffusion.

Text-based person search aims to retrieve the most relevant pedestrian images from an image gallery based on textual descriptions. Most existing methods rely on two separate encoders to extract the image and text features, and then elaborately design various schemes to bridge the gap between image and text modalities. However, the shallow interaction between both modalities in these methods is still insufficient to eliminate the modality gap. To address the above problem, we propose TransTPS, a transformer-based framework that enables deeper interaction between both modalities through the self-attention mechanism in transformer, effectively alleviating the modality gap. In addition, due to the small inter-class variance and large intra-class variance in image modality, we further develop two techniques to overcome these limitations. Specifically, Cross-modal Multi-Granularity Matching (CMGM) is proposed to address the problem caused by small inter-class variance and facilitate distinguishing pedestrians with similar appearance. Besides, Contrastive Loss with Weakly Positive pairs (CLWP) is introduced to mitigate the impact of large intra-class variance and contribute to the retrieval of more target images. Experiments on CUHK-PEDES and RSTPReID datasets demonstrate that our proposed framework achieves state-of-the-art performance compared to previous methods.

Text-guided image editing models have shown remarkable results. However, there remain two problems. First, they employ fixed manipulation modules for various editing requirements (e.g., color changing, texture changing, content adding and removing), which results in over-editing or insufficient editing. Second, they do not clearly distinguish between text-required and text-irrelevant parts, which leads to inaccurate editing. To solve these limitations, we propose: (i) a Dynamic Editing Block (DEBlock) that composes different editing modules dynamically for various editing requirements. (ii) a Composition Predictor (Comp-Pred), which predicts the composition weights for DEBlock according to the inference on target texts and source images. (iii) a Dynamic text-adaptive Convolution Block (DCBlock) that queries source image features to distinguish text-required parts and text-irrelevant parts. Extensive experiments demonstrate that our DE-Net achieves excellent performance and manipulates source images more correctly and accurately.

In this paper, we present an integral pre-training framework based on masked image modeling (MIM). We advocate for pre-training the backbone and neck jointly so that the transfer gap between MIM and downstream recognition tasks is minimal. We make two technical contributions. First, we unify the reconstruction and recognition necks by inserting a feature pyramid into the pre-training stage. Second, we complement mask image modeling (MIM) with masked feature modeling (MFM) that offers multi-stage supervision to the feature pyramid. The pre-trained models, termed integrally pre-trained transformer pyramid networks (iTPNs), serve as powerful foundation models for visual recognition. In particular, the base/large-level iTPN achieves an 86.2%/87.8% top-1 accuracy on ImageNet-1K, a 53.2%/55.6% box AP on COCO object detection with 1× training schedule using Mask-RCNN, and a 54.7%/57.7% mIoU on ADE20K semantic segmentation using UPerHead – all these results set new records. Our work inspires the community to work on unifying upstream pre-training and downstream fine-tuning tasks. Code is available at github.com/sunsmarterjie/iTPN.

Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter- and data- efficient way, by learning the "soft prompts" to condition frozen pretraining models. Though effective, it is particularly problematic in the few-shot scenario, where prompt tuning performance is sensitive to the initialization and requires a time-consuming process to find a good initialization, thus restricting the fast adaptation ability of the pre-training models. In addition, prompt tuning could undermine the generalizability of the pre-training models, because the learnable prompt tokens are easy to overfit to the limited training samples. To address these issues, we introduce a novel Gradient-RegulAted Meta-prompt learning (GRAM) framework that jointly meta-learns an efficient soft prompt initialization for better adaptation and a lightweight gradient regulating function for strong cross-domain generalizability in a meta-learning paradigm using only the unlabeled image-text pre-training data. Rather than designing a specific prompt tuning method, our GRAM can be easily incorporated into various prompt tuning methods in a model-agnostic way, and comprehensive experiments show that GRAM brings about consistent improvement for them in several settings (i.e., few-shot learning, cross-domain generalization, cross-dataset generalization, etc.) over 11 datasets. Further, experiments show that GRAM enables the orthogonal methods of textual and visual prompt tuning to work in a mutually-enhanced way, offering better generalizability beyond the uni-modal prompt tuning methods.

Large-scale multi-modal contrastive learning frameworks like CLIP typically require a large amount of image-text samples for training. However, these samples are always collected continuously in real scenarios. This paper discusses the feasibility of continual CLIP training using streaming data. Unlike continual learning based on self-supervised learning methods for pure images, which is empirically robust against catastrophic forgetting, CLIP’s performance degeneration in the continual setting is significant and non-neglectable. By analyzing the changes in the model’s representation space during continual CLIP training from a spatial geometry perspective, we explore and summarize these spatial variations as Spatial Disorder (SD), which can be divided into Intra-modal Rotation and Inter-modal Deviation. Moreover, we empirically and theoretically demonstrate how SD leads to a performance decline for CLIP on cross-modal retrieval tasks. To alleviate SD, we propose a new continual vision-language representation learning framework Mod-X: Maintain off-diagonal information-matriX. By selectively aligning the off-diagonal information distribution of contrastive matrices, the Mod-X improves the capability of the multi-modal model by maintaining the multi-modal representation space alignment on the old data domain during continuously fitting the new training data domain. Experiments on commonly used datasets with different scales and scopes have demonstrated the effectiveness of our method.

Recent score-based diffusion models (SBDMs) show promising results in unpaired image-to-image translation (I2I). However, existing methods, either energy-based or statistically-based, provide no explicit form of the interfered intermediate generative distributions. This work presents a new score-decomposed diffusion model (SDDM) on manifolds to explicitly optimize the tangled distributions during image generation. SDDM derives manifolds to make the distributions of adjacent time steps separable and decompose the score function or energy guidance into an image "denoising" part and a content "refinement" part. To refine the image in the same noise level, we equalize the refinement parts of the score function and energy guidance, which permits multi-objective optimization on the manifold. We also leverage the block adaptive instance normalization module to construct manifolds with lower dimensions but still concentrated with the perturbed reference image. SDDM outperforms existing SBDM-based methods with much fewer diffusion steps on several I2I benchmarks.

Owing to the unrestricted nature of the content in the training data, large text-to-image diffusion models, such as Stable Diffusion (SD), are capable of generating images with potentially copyrighted or dangerous content based on corresponding textual concepts information. This includes specific intellectual property (IP), human faces, and various artistic styles. However, Negative Prompt, a widely used method for content removal, frequently fails to conceal this content due to inherent limitations in its inference logic. In this work, we propose a novel strategy named Degeneration-Tuning (DT) to shield contents of unwanted concepts from SD weights. By utilizing Scrambled Grid to reconstruct the correlation between undesired concepts and their corresponding image domain, we guide SD to generate meaningless content when such textual concepts are provided as input. As this adaptation occurs at the level of the model's weights, the SD, after DT, can be grafted onto other conditional diffusion frameworks like ControlNet to shield unwanted concepts. In addition to qualitatively showcasing the effectiveness of our DT method in protecting various types of concepts, a quantitative comparison of the SD before and after DT indicates that the DT method does not significantly impact the generative quality of other contents. The FID and IS scores of the model on COCO-30K exhibit only minor changes after DT, shifting from 12.61 and 39.20 to 13.04 and 38.25, respectively, which clearly outperforms the previous methods.

Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to fully-supervised methods, seeming to deliver the message that human labels hardly contribute to learning transferrable visual features. In this paper, we defend the usefulness of semantic labels but point out that fully-supervised and self-supervised methods are pursuing different kinds of features. To alleviate this issue, we present a new algorithm named Supervised Contrastive Adjustment in Neighborhood (SCAN) that maximally prevents the semantic guidance from damaging the appearance feature embedding. In a series of downstream tasks, SCAN achieves superior performance compared to previous fully-supervised and self-supervised methods, and sometimes the gain is significant. More importantly, our study reveals that semantic labels are useful in assisting self-supervised methods, opening a new direction for the community.

Meta-learning enables models to adapt to new environments rapidly with a few training examples. Current gradient-based meta-learning methods concentrate on finding good model-agnostic initialization (meta-weights) for learners. In this paper, we aim to obtain better meta-learners by co-optimizing the architecture and meta-weights simultaneously. Existing NAS-based meta-learning methods apply a two-stage strategy, i.e., first searching architectures and then re-training meta-weights on the searched architecture. However, this two-stage strategy would break the mutual impact of the architecture and meta-weights since they are optimized separately. Differently, we propose progressive connection consolidation, fixing the architecture layer by layer, in which the layer with the largest weight value would be fixed first. In this way, we can jointly search architectures and train the meta-weights on fixed layers. Besides, to improve the generalization performance of the searched meta-learner on all tasks, we propose a more effective rule for co-optimization, namely Connection-Adaptive Meta-learning (CAML). By searching only once, we can obtain both adaptive architecture and meta-weights for meta-learning. Extensive experiments show that our method achieves state-of-the-art performance with 3x less computational cost, revealing our method's effectiveness and efficiency.

Understanding human emotions is a crucial ability for intelligent robots to provide better human-robot interactions. The existing works are limited to trimmed video-level emotion classification, failing to locate the temporal window corresponding to the emotion. In this paper, we introduce a new task, named Temporal Emotion Localization in videos (TEL), which aims to detect human emotions and localize their corresponding temporal boundaries in untrimmed videos with aligned subtitles. TEL presents three unique challenges compared to temporal action localization: 1) The emotions have extremely varied temporal dynamics; 2) The emotion cues are embedded in both appearances and complex plots; 3) The fine-grained temporal annotations are complicated and labor-intensive. To address the first two challenges, we propose a novel dilated context integrated network with a coarse-fine two-stream architecture. The coarse stream captures varied temporal dynamics by modeling multi-granularity temporal contexts. The fine stream achieves complex plots understanding by reasoning the dependency between the multi-granularity temporal contexts from the coarse stream and adaptively integrates them into fine-grained video segment features. To address the third challenge, we introduce a cross-modal consensus learning paradigm, which leverages the inherent semantic consensus between the aligned video and subtitle to achieve weakly-supervised learning. We contribute a new testing set with 3,000 manually-annotated temporal boundaries so that future research on the TEL problem can be quantitatively evaluated. Extensive experiments show the effectiveness of our approach on temporal emotion localization. The repository of this work is at https://github.com/YYJMJC/TemporalEmotion-Localization-in-Videos.

Large-scale vision-language pre-training has shown impressive advances in a wide range of downstream tasks. Existing methods mainly model the cross-modal alignment by the similarity of the global representations of images and text, or advanced cross-modal attention upon image and text features. However, they fail to explicitly learn the fine-grained semantic alignment between visual regions and textual phrases, as only global image-text alignment information is available. In this paper, we introduce LOUPE, a fine-grained semantically aLigned visiOn-langUage PrE-training framework, which learns fine-grained semantic alignment from the novel perspective of game-theoretic interactions. To efficiently estimate the game-theoretic interactions, we further propose an uncertainty-aware neural Shapley interaction learning module. Experiments show that LOUPE achieves state-of-the-art performance on a variety of vision-language tasks. Without any object-level human annotations and fine-tuning, LOUPE achieves competitive performance on object detection and visual grounding. More importantly, LOUPE opens a new promising direction of learning fine-grained semantics from large-scale raw image-text pairs.

Person re-identification (ReID) aims at matching identities across disjoint cameras. Its fundamental difficulty lies in associating images across individual cameras, where a key clue,i.e., identity appearance, is prone to the environmental factors of cameras and, consequently, subject to distinct image distributions due to the environmental differences between cameras. To associate images from training cameras, ReID methods strongly demand expensive inter-camera annotations for learning the relations between the distribution of these cameras, yet trained models are still not guaranteed to transfer well to unseen cameras. This problem significantly limits the application of ReID. This paper rethinks the working mechanism of conventional ReID approaches and puts forward a new solution. With an effective operator named Camera-based Batch Normalization (CBN), we guarantee an invariant input distribution independent of all cameras. Thus, the training and testing procedures are always conducted under the same input distribution. This alignment brings three benefits. First, ReID models enjoy better abilities to generalize across testing scenarios with unseen cameras and transfer across multiple training sets. Second, it makes better use of intra-camera annotations, which have been undervalued before due to the lack of cross-camera information. Ideally, the cost of inter-camera annotations can be largely reduced. Third, cross-modality tasks can be better defined through aligning visible/infrared cameras’ distributions. Experiments on a wide range of ReID tasks demonstrate the effectiveness of our approach.

Unsupervised pretraining is of great significance for visual representation. Especially, contrastive learning has achieved great success recently, but existing approaches mostly ignored spatial information which is often crucial for visual representation. Strong semantic embedding has an inherent advantage for classification, but dense prediction tasks require more spatial and low-level representation. This paper presentsheterogeneous contrastive learning(HCL), an effective approach that adds spatial information to the encoding stage to alleviate the learning inconsistency between the contrastive objective and strong data augmentation operations. We demonstrate the effectiveness of HCL by showing that (i) it achieves higher accuracy in instance discrimination, (ii) it surpasses existing pre-training methods in a series of downstream tasks (iii) and it shrinks the pre-training costs by half for almost 800 GPU-hours. More importantly, we show that our approach achieves higher efficiency in visual representations, and thus delivers a key message to inspire the future research of self-supervised visual representation learning.

Neural architecture search has attracted wide attentions in both academia and industry. To accelerate it, researchers proposed weight-sharing methods which first train a super-network to reuse computation among different operators, from which exponentially many sub-networks can be sampled and efficiently evaluated. These methods enjoy great advantages in terms of computational costs, but the sampled sub-networks are not guaranteed to be estimated precisely unless an individual training process is taken. This paper owes such inaccuracy to the inevitable mismatch between assembled network layers, so that there is a random error term added to each estimation. We alleviate this issue by training a graph convolutional network to fit the performance of sampled sub-networks so that the impact of random errors becomes minimal. With this strategy, we achieve a higher rank correlation coefficient in the selected set of candidates, which consequently leads to better performance of the final architecture. In addition, our approach also enjoys the flexibility of being used under different hardware constraints, since the graph convolutional network has provided an efficient lookup table of the performance of architectures in the entire search space.

The main difficulty of person re-identification (ReID) lies in collecting annotated data and transferring the model across different domains. This paper presents UnrealPerson, a novel pipeline that makes full use of unreal image data to decrease the costs in both the training and deployment stages. Its fundamental part is a system that can generate synthesized images of high-quality and from controllable distributions. Instance-level annotation goes with the synthesized data and is almost free. We point out some details in image synthesis that largely impact the data quality. With 3,000 IDs and 120,000 instances, our method achieves a 38.5% rank-1 accuracy when being directly transferred to MSMT17. It almost doubles the former record using synthesized data and even surpasses previous direct transfer records using real data. This offers a good basis for unsupervised domain adaption, where our pre-trained model is easily plugged into the state-of-the-art algorithms towards higher accuracy. In addition, the data distribution can be flexibly adjusted to fit some corner ReID scenarios, which widens the application of our pipeline. We publish our data synthesis toolkit and synthesized data in https://github.com/FlyHighest/UnrealPerson.

The past year has witnessed the rapid development of applying the Transformer module to vision problems. While some researchers have demonstrated that Transformer-based models enjoy a favorable ability of fitting data, there are still growing number of evidences showing that these models suffer over-fitting especially when the training data is limited. This paper offers an empirical study by performing step-by-step operations to gradually transit a Transformer-based model to a convolution-based model. The results we obtain during the transition process deliver useful messages for improving visual recognition. Based on these observations, we propose a new architecture named Visformer, which is abbreviated from the ‘Vision-friendly Transformer’. With the same computational complexity, Visformer outperforms both the Transformer-based and convolution-based models in terms of ImageNet classification accuracy, and the advantage becomes more significant when the model complexity is lower or the training set is smaller. The code is available at https://github.com/danczs/Visformer.

The category gap between training and evaluation has been characterised as one of the main obstacles to the success of Few-Shot Learning (FSL). In this paper, we for the first time empirically identify image background, common in realistic images, as a shortcut knowledge helpful for in-class classification but ungeneralizable beyond training categories in FSL. A novel framework, COSOC, is designed to tackle this problem by extracting foreground objects in images at both training and evaluation without any extra supervision. Extensive experiments carried on inductive FSL tasks demonstrate the effectiveness of our approaches.

Person re-identification (ReID) aims at finding the same person in different cameras. Training such systems usually requires a large amount of cross-camera pedestrians to be annotated from surveillance videos, which is labor-consuming especially when the number of cameras is large. Differently, this paper investigates ReID in an unexplored single-camera-training (SCT) setting, where each person in the training set appears in only one camera. To the best of our knowledge, this setting was never studied before. SCT enjoys the advantage of low-cost data collection and annotation, and thus eases ReID systems to be trained in a brand new environment. However, it raises major challenges due to the lack of cross-camera person occurrences, which conventional approaches heavily rely on to extract discriminative features. The key to dealing with the challenges in the SCT setting lies in designing an effective mechanism to complement cross-camera annotation. We start with a regular deep network for feature extraction, upon which we propose a novel loss function named multi-camera negative loss (MCNL). This is a metric learning loss motivated by probability, suggesting that in a multi-camera system, one image is more likely to be closer to the most similar negative sample in other cameras than to the most similar negative sample in the same camera. In experiments, MCNL significantly boosts ReID accuracy in the SCT setting, which paves the way of fast deployment of ReID systems with good performance on new target scenes.

Automatic designing computationally efficient neural networks has received much attention in recent years. Existing approaches either utilize network pruning or leverage the network architecture search methods. This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs, so that under each network configuration, one can estimate the FLOPs utilization ratio (FUR) for each layer and use it to determine whether to increase or decrease the number of channels on the layer. Note that FUR, like the gradient of a non-linear function, is accurate only in a small neighborhood of the current network. Hence, we design an iterative mechanism so that the initial network undergoes a number of steps, each of which has a small 'adjusting rate' to control the changes to the network. The computational overhead of the entire search process is reasonable, i.e., comparable to that of re-training the final model from scratch. Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach, which consistently outperforms the pruning counterpart. The code is available at https://github.com/danczs/NetworkAdjustment.

The huge variance of human pose and the misalign-ment of detected human images significantly increase the difficulty of pedestrian image matching in person Re-Identification (Re-ID). Moreover, the massive visual data being produced by surveillance video cameras requires highly efficient person Re-ID systems. Targeting to solve the first problem, this work proposes a robust and discriminative pedestrian image descriptor, namely, the Global-Local-Alignment Descriptor (GLAD). For the second problem, this work treats person Re-ID as image retrieval and proposes an efficient indexing and retrieval framework. GLAD explicitly leverages the local and global cues in the human body to generate a discriminative and robust representation. It consists of part extraction and descriptor learning modules, where several part regions are first detected and then deep neural networks are designed for representation learning on both the local and global regions. A hierarchical indexing and retrieval framework is designed to perform offline relevance mining to eliminate the huge person ID redundancy in the gallery set, and accelerate the online Re-ID procedure. Extensive experimental results on widely used public benchmark datasets show GLAD achieves competitive accuracy compared to the state-of-the-art methods. On a large-scale person, with the Re-ID dataset containing more than 520 K images, our retrieval framework significantly accelerates the online Re-ID procedure while also improving Re-ID accuracy. Therefore, this work has the potential to work better on person Re-ID tasks in real scenarios.

Although the performance of person Re-Identification (ReID) has been significantly boosted, many challenging issues in real scenarios have not been fully investigated, e.g., the complex scenes and lighting variations, viewpoint and pose changes, and the large number of identities in a camera network. To facilitate the research towards conquering those issues, this paper contributes a new dataset called MSMT171 with many important features, e.g., 1) the raw videos are taken by an 15-camera network deployed in both indoor and outdoor scenes, 2) the videos cover a long period of time and present complex lighting variations, and 3) it contains currently the largest number of annotated identities, i.e., 4,101 identities and 126,441 bounding boxes. We also observe that, domain gap commonly exists between datasets, which essentially causes severe performance drop when training and testing on different datasets. This results in that available training data cannot be effectively leveraged for new testing domains. To relieve the expensive costs of annotating new training samples, we propose a Person Transfer Generative Adversarial Network (PTGAN) to bridge the domain gap. Comprehensive experiments show that the domain gap could be substantially narrowed-down by the PTGAN.

With the capability of locating and tracking specific suspects or vehicles in a large camera network, person Re-Identification (ReID) and vehicle ReID show potential to be a key technology in smart surveillance system. They have been drawing lots of attentions from both academia and industry. To demonstrate our recent research progresses on those two tasks, we develop a robust and efficient person and video ReID system named as VP-ReID. This system is build based on our recent works including Deep Convolutional Neural Network design for discriminative feature extraction, efficient off-line indexing, as well as distance metric optimization for deep feature learning. Constructed upon those algorithms, VP-ReID identifies query vehicle and person efficiently and accurately from a large gallery set.

The huge variance of human pose and the misalignment of detected human images significantly increase the difficulty of person Re-Identification (Re-ID). Moreover, efficient Re-ID systems are required to cope with the massive visual data being produced by video surveillance systems. Targeting to solve these problems, this work proposes a Global-Local-Alignment Descriptor (GLAD) and an efficient indexing and retrieval framework, respectively. GLAD explicitly leverages the local and global cues in human body to generate a discriminative and robust representation. It consists of part extraction and descriptor learning modules, where several part regions are first detected and then deep neural networks are designed for representation learning on both the local and global regions. A hierarchical indexing and retrieval framework is designed to eliminate the huge redundancy in the gallery set, and accelerate the online Re-ID procedure. Extensive experimental results show GLAD achieves competitive accuracy compared to the state-of-the-art methods. Our retrieval framework significantly accelerates the online Re-ID procedure without loss of accuracy. Therefore, this work has potential to work better on person Re-ID tasks in real scenarios.