Existing multimodal generative models fall short as qualified design copilots, as they often struggle to generate imaginative outputs once instructions are less detailed or lack the ability to maintain consistency with the provided references. In this work, we introduce WeGen, a model that unifies multimodal generation and understanding, and promotes their interplay in iterative generation. It can generate diverse results with high creativity for less detailed instructions. And it can progressively refine prior generation results or integrating specific contents from references following the instructions in its chat with users. During this process, it is capable of preserving consistency in the parts that the user is already satisfied with. To this end, we curate a large-scale dataset, extracted from Internet videos, containing rich object dynamics and auto-labeled dynamics descriptions by advanced foundation models to date. These two information are interleaved into a single sequence to enable WeGen to learn consistency-aware generation where the specified dynamics are generated while the consistency of unspecified content is preserved aligned with instructions. Besides, we introduce a prompt self-rewriting mechanism to enhance generation diversity. Extensive experiments demonstrate the effectiveness of unifying multimodal understanding and generation in WeGen and show it achieves state-of-the-art performance across various visual generation benchmarks. These also demonstrate the potential of WeGen as a user-friendly design copilot as desired. The code and models will be available at https://github.com/hzphzp/WeGen.

Understanding and reasoning about the 4D space-time is crucial for Vision-and-Language Navigation (VLN). However, previous works lack in-depth exploration in this aspect, resulting in bottlenecked spatial perception and action precision of VLN agents. In this work, we introduce NaVid-4D, a Vision Language Model (VLM) based navigation agent taking the lead in explicitly showcasing the capabilities of spatial intelligence in the real world. Given natural language instructions, NaVid-4D requires only egocentric RGB-D video streams as observations to perform spatial understanding and reasoning for generating precise instruction-following robotic actions. NaVid-4D learns navigation policies using the data from simulation environments and is endowed with precise spatial understanding and reasoning capabilities using web data. Without the need to pre-train an RGB-D foundation model, we propose a method capable of directly injecting the depth features into the visual encoder of a VLM. We further compare the use of factually captured depth information with the monocularly estimated one and find NaVid-4D works well with both while using estimated depth offers greater gener-alization capability and better mitigates the sim-to-real gap. Extensive experiments demonstrate that NaVid-4D achieves state-of-the-art performance in simulation environment and makes impressive VLN performance with spatial intelligence happen in the real world.

Significant progress has been made in scene text detection models since the rise of deep learning, but scene text layout analysis, which aims to group detected text instances as paragraphs, has not kept pace. Previous works either treated text detection and grouping using separate models, or train a model from scratch while using a unified one. All of them have not yet made full use of the already well-trained text detectors and easily obtainable detection datasets. In this paper, we present Text Grouping Adapter (TGA), a module that can enable the utilization of various pretrained text detectors to learn layout analysis, allowing us to adopt a well-trained text detector right off the shelf or just fine-tune it efficiently. Designed to be compatible with various text detector architectures, TGA takes detected text regions and image features as universal inputs to as-semble text instance features. To capture broader contextual information for layout analysis, we propose to predict text group masks from text instance features by one-to-many assignment. Our comprehensive experiments demonstrate that, even with frozen pretrained models, incorporating our TGA into various pretrained text detectors and text spotters can achieve superior layout analysis performance, simultaneously inheriting generalized text detection ability from pretraining. In the case of full parameter fine-tuning, we can further improve layout analysis performance.

Generative Adversarial Networks (GANs) have been widely used to recover vivid textures in image super-resolution (SR) tasks. In particular, one discriminator is utilized to enable the SR network to learn the distribution of real-world high-quality images in an adversarial training manner. However, the distribution learning is overly coarse-grained, which is susceptible to virtual textures and causes counter-intuitive generation results. To mitigate this, we propose the simple and effective Semantic-aware Discriminator (denoted as SeD), which encourages the SR network to learn the fine-grained distributions by introducing the semantics of images as a condition. Concretely, we aim to excavate the semantics of images from a well-trained semantic extractor. Under different semantics, the discriminator is able to distinguish the real-fake images individually and adaptively, which guides the SR network to learn the more fine-grained semantic-aware textures. To obtain accurate and abundant semantics, we take full advantage of recently popular pretrained vision models (PVMs) with extensive datasets, and then incorporate its semantic features into the discriminator through a well-designed spatial cross-attention module. In this way, our proposed semantic-aware discriminator empowered the SR network to produce more photo-realistic and pleasing images. Extensive experiments on two typical tasks, i.e., SR and Real SR have demonstrated the effectiveness of our proposed methods. The code will be available at https://github.com/1bc12345/SeD.

Most Neural Radiance Fields (NeRFs) exhibit limited generalization capabilities,which restrict their applicability in representing multiple scenes using a single model. To address this problem, existing generalizable NeRF methods simply condition the model on image features. These methods still struggle to learn precise global representations over diverse scenes since they lack an effective mechanism for interacting among different points and views. In this work, we unveil that 3D implicit representation learning can be significantly improved by mask-based modeling. Specifically, we propose **m**asked **r**ay and **v**iew **m**odeling for generalizable **NeRF** (**MRVM-NeRF**), which is a self-supervised pretraining target to predict complete scene representations from partially masked features along each ray. With this pretraining target, MRVM-NeRF enables better use of correlations across different rays and views as the geometry priors, which thereby strengthens the capability of capturing intricate details within the scenes and boosts the generalization capability across different scenes. Extensive experiments demonstrate the effectiveness of our proposed MRVM-NeRF on both synthetic and real-world datasets, qualitatively and quantitatively. Besides, we also conduct experiments to show the compatibility of our proposed method with various backbones and its superiority under few-shot cases.

Data augmentation (DA) has been extensively studied to facilitate model optimization in many tasks. Prior DA works focus on designing augmentation operations themselves, while leaving selecting suitable samples for augmentation out of consideration. This might incur visual ambiguities and further induce training biases. In this paper, we propose an effective approach, dubbed SelectAugment, to select samples for augmentation in a deterministic and online manner based on the sample contents and the network training status. To facilitate the policy learning, in each batch, we exploit the hierarchy of this task by first determining the augmentation ratio and then deciding whether to augment each training sample under this ratio. We model this process as two-step decision-making and adopt Hierarchical Reinforcement Learning (HRL) to learn the selection policy. In this way, the negative effects of the randomness in selecting samples to augment can be effectively alleviated and the effectiveness of DA is improved. Extensive experiments demonstrate that our proposed SelectAugment significantly improves various off-the-shelf DA methods on image classification and fine-grained image recognition.

The three existing dominant network families, i.e., CNNs, Transformers and MLPs, differ from each other mainly in the ways of fusing spatial contextual information, leaving designing more effective token-mixing mechanisms at the core of backbone architecture development. In this work, we propose an innovative token-mixer, dubbed Active Token Mixer (ATM), to actively incorporate contextual information from other tokens in the global scope into the given query token. This fundamental operator actively predicts where to capture useful contexts and learns how to fuse the captured contexts with the query token at channel level. In this way, the spatial range of token-mixing can be expanded to a global scope with limited computational complexity, where the way of token-mixing is reformed. We take ATMs as the primary operators and assemble them into a cascade architecture, dubbed ATMNet. Extensive experiments demonstrate that ATMNet is generally applicable and comprehensively surpasses different families of SOTA vision backbones by a clear margin on a broad range of vision tasks, including visual recognition and dense prediction tasks. Code is available at https://github.com/microsoft/ActiveMLP.

Layout generation aims to synthesize realistic graphic scenes consisting of elements with different attributes in-cluding category, size, position, and between-element relation. It is a crucial task for reducing the burden on heavyduty graphic design works for formatted scenes, e.g., publications, documents, and user interfaces (UIs). Diverse application scenarios impose a big challenge in unifying various layout generation subtasks, including conditional and unconditional generation. In this paper, we propose a Layout Diffusion Generative Model (LDGM) to achieve such unification with a single decoupled diffusion model. LDGM views a layout of arbitrary missing or coarse element attributes as an intermediate diffusion status from a completed layout. Since different attributes have their individual semantics and characteristics, we propose to decouple the diffusion processes for them to improve the diversity of training samples and learn the reverse process jointly to exploit global-scope contexts for facilitating generation. As a result, our LDGM can generate layouts either from scratch or conditional on arbitrary available attributes. Extensive qualitative and quantitative experiments demonstrate our proposed LDGM outperforms existing layout generation models in both functionality and performance.

Improving the generalization ability of Deep Neural Networks (DNNs) is critical for their practical uses, which has been a longstanding challenge. Some theoretical studies have uncovered that DNNs have preferences for some frequency components in the learning process and indicated that this may affect the robustness of learned features. In this paper, we propose Deep Frequency Filtering (DFF)for learning domain-generalizable features, which is the first endeavour to explicitly modulate the frequency components of different transfer difficulties across domains in the latent space during training. To achieve this, we perform Fast Fourier Transform (FFT) for the feature maps at different layers, then adopt a light-weight module to learn attention masks from the frequency representations after FFT to enhance transferable components while suppressing the components not conducive to generalization. Further, we empirically compare the effectiveness of adopting different types of attention designs for implementing DFF. Extensive experiments demonstrate the effectiveness of our proposed DFF and show that applying our DFF on a plain baseline out-performs the state-of-the-art methods on different domain generalization tasks, including close-set classification and open-set retrieval.

Recent vision transformers, large-kernel CNNs and MLPs have attained remarkable successes in broad vision tasks thanks to their effective information fusion in the global scope. However, their efficient deployments, especially on mobile devices, still suffer from noteworthy challenges due to the heavy computational costs of self-attention mechanisms, large kernels, or fully connected layers. In this work, we apply conventional convolution theorem to deep learning for addressing this and reveal that adaptive frequency filters can serve as efficient global token mixers. With this insight, we propose Adaptive Frequency Filtering (AFF) token mixer. This neural operator transfers a latent representation to the frequency domain via a Fourier transform and performs semantic-adaptive frequency filtering via an elementwise multiplication, which mathematically equals to a token mixing operation in the original latent space with a dynamic convolution kernel as large as the spatial resolution of this latent representation. We take AFF token mixers as primary neural operators to build a lightweight neural network, dubbed AFFNet. Extensive experiments demonstrate the effectiveness of our proposed AFF token mixer and show that AFFNet achieve superior accuracy and efficiency trade-offs compared to other lightweight network designs on broad visual tasks, including visual recognition and dense prediction tasks. Code is available at https://github.com/microsoft/TokenMixers.

Targeting for detecting anomalies of various sizes for complicated normal patterns, we propose a Template-guided Hierarchical Feature Restoration method, which introduces two key techniques, bottleneck compression and template-guided compensation, for anomaly-free feature restoration. Specially, our framework compresses hierarchical features of an image by bottleneck structure to preserve the most crucial features shared among normal samples. We design template-guided compensation to restore the distorted features towards anomaly-free features. Particularly, we choose the most similar normal sample as the template, and leverage hierarchical features from the template to compensate the distorted features. The bottleneck could partially filter out anomaly features, while the compensation further converts the reminding anomaly features towards normal with template guidance. Finally, anomalies are detected in terms of the cosine distance between the pre-trained features of an inference image and the corresponding restored anomaly-free features. Experimental results demonstrate the effectiveness of our approach, which achieves the state-of-the-art performance on the MVTec LOCO AD dataset.

Re-Identification has been widely leverage by tracking-by-detection Multi-Object Tracking methods to enhance the matching step. During training, Re-Identification is usually learned as a sub-task considering the projected centroid of the bounding boxes as the embedding tensor. This design is problematic for Re-Identification feature learning and leveraging because of the noise introduced by the big amount of occlusions. Specifically, the occlusion between objects of the target class causes embedding tensors to represent objects with wrong IDs and this specific scenario has been overlooked in previous literature. In this work we introduce an Adaptive use of Re-Identification features that aims to tackle this problem by using Re-Identification features only when they are reliable. Our method is generic and can be added to further boost performance to any Multi-Object Tracking method that uses Re-Identification. Results in multiple datasets using various base methods demonstrate the consistency of our method with state-of-the-art results.

This paper explores the connection between learning trajectories of Deep Neural Networks (DNNs) and their generalization capabilities when optimized using (stochastic) gradient descent algorithms. Instead of concentrating solely on the generalization error of the DNN post-training, we present a novel perspective for analyzing generalization error by investigating the contribution of each update step to the change in generalization error. This perspective enable a more direct comprehension of how the learning trajectory influences generalization error. Building upon this analysis, we propose a new generalization bound that incorporates more extensive trajectory information. Our proposed generalization bound depends on the complexity of learning trajectory and the ratio between the bias and diversity of training set. Experimental observations reveal that our method effectively captures the generalization error throughout the training process. Furthermore, our approach can also track changes in generalization error when adjustments are made to learning rates and label noise levels. These results demonstrate that learning trajectory information is a valuable indicator of a model's generalization capabilities.

In the Internet era, the explosive growth of media data processing poses significant challenges for the research of Image Coding for Machines (ICM) in improving the efficiency of AI models while reducing the burdens of data storage and transmission. Existing ICM methods face challenges in achieving sufficient generalization ability when developing a single codec to handle diverse downstream tasks. To address these issues, we propose a unified ICM framework that facilitates diverse downstream tasks with a novel importance allocation mechanism. Equipped with a spatially variable-rate image compression codec, we introduce two options: online updating and offline predicting the non-uniform quality map, which governs the quality distribution of reconstructed images based on specific downstream tasks. Our proposed method is rigorously evaluated through extensive experiments on diverse and comprehensive fine-grained image classification datasets. The experiment results conclusively demonstrate the effectiveness of the proposed method in achieving a superior rate-distortion trade-off for ICM.

Multi-camera tracking systems are gaining popularity in applications that demand high-quality tracking results, such as frictionless checkout. In cluttered and crowded environments, monocular multi-object tracking (MOT) systems often fail due to occlusions. Multiple highly overlapped cameras are capable of recovering partial 3D information. When used properly, 3D data can significantly alleviate the occlusion issue. However, training a multi-camera tracker demands a large-scale multi-camera tracking dataset with diverse camera settings and backgrounds. These requirements make the collection of multi-camera tracking dataset challenging and expensive. The cost of creating such a dataset has limited the availability and scale of datasets in this domain. Instead, we appeal to an auto-annotation system to reduce the cost, which uses overlapped and calibrated depth and RGB cameras to build a 3D tracker and automatically generates the 3D tracking results. The results are manually checked and corrected to ensure the label quality, which is much cheaper than solely manual annotation. Next, the 3D tracking results are projected to each calibrated RGB camera view to create 2D tracking results. In this way, we collect and annotate a large-scale densely labeled multi-camera tracking dataset from five different environments. We have conducted extensive experiments using two real-time multi-camera trackers and a person re-identification (ReID) model under different settings. This dataset provides a reliable benchmark for multi-camera, multi-object tracking systems in cluttered and crowded environments. We expect this benchmark to encourage more research attempts in this domain. Our dataset will be publicly released upon the acceptance of this work.

Neural video codecs have demonstrated great potential in video transmission and storage applications. Existing neural hybrid video coding approaches rely on optical flow or Gaussian-scale flow for prediction, which cannot support fine-grained adaptation to diverse motion content. Towards more content-adaptive prediction, we propose a novel cross-scale prediction module that achieves more effective motion compensation. Specifically, on the one hand, we produce a reference feature pyramid as prediction sources and then transmit cross-scale flows that leverage the feature scale to control the precision of prediction. On the other hand, for the first time, a weighted prediction mechanism is introduced even if only a single reference frame is available, which can help synthesize a fine prediction result by transmitting cross-scale weight maps. In addition to the cross-scale prediction module, we further propose a multi-stage quantization strategy, which improves the rate-distortion performance with no extra computational penalty during inference. We show the encouraging performance of our efficient neural video codec (ENVC) on several benchmark datasets. In particular, the proposed ENVC can compete with the latest coding standard H.266/VVC in terms of sRGB PSNR on UVG dataset for the low-latency mode. We also analyze in detail the effectiveness of the cross-scale prediction module in handling various video content, and provide a comprehensive ablation study to analyze those important components. Test code is available at https://github.com/USTC-IMCL/ENVC.

Unsupervised domain adaptive person re-identification (ReID) has been extensively investigated to mitigate the adverse effects of domain gaps. Those works assume the target domain data can be accessible all at once. However, for the real-world streaming data, this hinders the timely adaptation to changing data statistics and sufficient exploitation of increasing samples. In this paper, to address more practical scenarios, we propose a new task, Lifelong Un-supervised Domain Adaptive (LUDA) person ReID. This is challenging because it requires the model to continuously adapt to unlabeled data in the target environments while alleviating catastrophic forgetting for such a fine-grained person retrieval task. We design an effective scheme for this task, dubbed CLUDA-ReID, where the anti-forgetting is harmoniously coordinated with the adaptation. Specifically, a meta-based Coordinated Data Replay strategy is proposed to replay old data and update the network with a coordinated optimization direction for both adaptation and memorization. Moreover, we propose Relational Consistency Learning for old knowledge distillation/inheritance in line with the objective of retrieval-based tasks. We set up two evaluation settings to simulate the practical application scenarios. Extensive experiments demonstrate the effectiveness of our CLUDA-ReID for both scenarios with stationary target streams and scenarios with dynamic target streams.

For deep reinforcement learning (RL) from pixels, learning effective state representations is crucial for achieving high performance. However, in practice, limited experience and high-dimensional inputs prevent effective representation learning. To address this, motivated by the success of mask-based modeling in other research fields, we introduce mask-based reconstruction to promote state representation learning in RL. Specifically, we propose a simple yet effective self-supervised method, Mask-based Latent Reconstruction (MLR), to predict complete state representations in the latent space from the observations with spatially and temporally masked pixels. MLR enables better use of context information when learning state representations to make them more informative, which facilitates the training of RL agents. Extensive experiments show that our MLR significantly improves the sample efficiency in RL and outperforms the state-of-the-art sample-efficient RL methods on multiple continuous and discrete control benchmarks. Our code is available at https://github.com/microsoft/Mask-based-Latent-Reconstruction.

Over the past several years, we have witnessed impressive progress in the field of learned image compression. Recent learned image codecs are commonly based on autoencoders, that first encode an image into low-dimensional latent representations and then decode them for reconstruction purposes. To capture spatial dependencies in the latent space, prior works exploit hyperprior and spatial context model to build an entropy model, which estimates the bit-rate for end-to-end rate-distortion optimization. However, such an entropy model is suboptimal from two aspects: (1) It fails to capture global-scope spatial correlations among the latents. (2) Cross-channel relationships of the latents remain unexplored. In this paper, we propose the concept of separate entropy coding to leverage a serial decoding process for causal contextual entropy prediction in the latent space. Acausal context modelis proposed that separates the latents across channels and makes use of channel-wise relationships to generate highly informative adjacent contexts. Furthermore, we propose acausal global prediction modelto find global reference points for accurate predictions of undecoded points. Both these two models facilitate entropy estimation without the transmission of overhead. In addition, we further adopt a new group-separated attention module to build more powerful transform networks. Experimental results demonstrate that our full image compression model outperforms standard VVC/H.266 codec on Kodak dataset in terms of both PSNR and MS-SSIM, yielding the state-of-the-art rate-distortion performance.

Recent works on learned image compression perform encoding and decoding processes in a full-resolution manner, resulting in two problems when deployed for practical applications. First, parallel acceleration of the autoregressive entropy model cannot be achieved due to serial decoding. Second, full-resolution inference often causes the out-of-memory (OOM) problem with limited GPU resources, especially for high-resolution images. Block partition is a good choice to handle the above issues, but it brings about new challenges in reducing the redundancy between blocks and eliminating block effects. To tackle the above challenges, this paper provides a learned block-based hybrid image compression (LBHIC) framework. Specifically, we introduce explicit intra prediction into a learned image compression framework to utilize the relation among adjacent blocks. Superior to context modeling by linear weighting of neighbor pixels in traditional codecs, we propose a contextual prediction module (CPM) to better capture long-range correlations by utilizing the strip pooling to extract the most relevant information in neighboring latent space, thus achieving effective information prediction. Moreover, to alleviate blocking artifacts, we further propose a boundary-aware postprocessing module (BPM) with the edge importance taken into account. Extensive experiments demonstrate that the proposed LBHIC codec outperforms the VVC, with a bit-rate conservation of 4.1%, and reduces the decoding time by approximately 86.7% compared with that of state-of-the-art learned image compression methods.

Person Re-identification (ReID) aims at matching a person of interest across images. In convolutional neural network (CNN) based approaches, loss design plays a vital role in pulling closer features of the same identity and pushing far apart features of different identities. In recent years, triplet loss achieves superior performance and is predominant in ReID. However, triplet loss considers only three instances of two classes in per-query optimization (with an anchor sample as query) and it is actually equivalent to a two-class classification. There is a lack of loss design which enables the joint optimization of multiple instances (of multiple classes) within per-query optimization for person ReID. In this paper, we introduce a multi-class classification loss,i.e., N-tuple loss, to jointly consider multiple ($N$) instances for per-query optimization. This in fact aligns better with the ReID test/inference process, which conducts the ranking/comparisons among multiple instances. Furthermore, for more efficient multi-class classification, we propose a new meta prototypical N-tuple loss. With the multi-class classification incorporated, our model achieves the state-of-the-art performance on the benchmark person ReID datasets

Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i.e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations. The key to solving this more challenging real image super-resolution (RealSR) problem lies in learning feature representations that are both informative and content-aware. In this paper, we propose a Omni-frequency Region-adaptive Network (OR-Net) to address both challenges, here we call features of all low, middle and high frequencies omni-frequency features. Specifically, we start from the frequency perspective and design a Frequency Decomposition (FD) module to separate different frequency components to comprehensively compensate the information lost for real LR image. Then, considering the different regions of real LR image have different frequency information lost, we further design a Region-adaptive Frequency Aggregation (RFA) module by leveraging dynamic convolution and spatial attention to adaptively restore frequency components for different regions. The extensive experiments endorse the high-efficient, effective, and scenario-agnostic nature of our OR-Net for RealSR.

Many unsupervised domain adaptive (UDA) person ReID approaches combine clustering-based pseudo-label prediction with feature fine-tuning. However, because of domain gap, the pseudo-labels are not always reliable and there are noisy/incorrect labels. This would mislead the feature representation learning and deteriorate the performance. In this paper, we propose to estimate and exploit the credibility of the assigned pseudo-label of each sample to alleviate the influence of noisy labels, by suppressing the contribution of noisy samples. We build our baseline framework using the mean teacher method together with an additional contrastive loss. We have observed that a sample with a wrong pseudo-label through clustering in general has a weaker consistency between the output of the mean teacher model and the student model. Based on this finding, we propose to exploit the uncertainty (measured by consistency levels) to evaluate the reliability of the pseudo-label of a sample and incorporate the uncertainty to re-weight its contribution within various ReID losses, including the ID classification loss per sample, the triplet loss, and the contrastive loss. Our uncertainty-guided optimization brings significant improvement and achieves the state-of-the-art performance on benchmark datasets.

Quantization is one of the core components in lossy image compression. For neural image compression, end-to-end optimization requires differentiable approximations of quantization, which can generally be grouped into three categories: additive uniform noise, straight-through estimator and soft-to-hard annealing. Training with additive uniform noise approximates the quantization error variationally but suffers from the train-test mismatch. The other two methods do not encounter this mismatch but, as shown in this paper, hurt the rate-distortion performance since the latent representation ability is weakened. We thus propose a novel soft-then-hard quantization strategy for neural image compression that first learns an expressive latent space softly, then closes the train-test mismatch with hard quantization. In addition, beyond the fixed integer-quantization, we apply scaled additive uniform noise to adaptively control the quantization granularity by deriving a new variational upper bound on actual rate. Experiments demonstrate that our proposed methods are easy to adopt, stable to train, and highly effective especially on complex compression models.

Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is classified by finding the nearest prototype from the support set based on their feature similarities. A neural network has different uncertainties on its calculated similarities of different pairs. Understanding and modeling the uncertainty on the similarity could promote the exploitation of limited samples in few-shot optimization. In this work, we propose Uncertainty-Aware Few-Shot framework for image classification by modeling uncertainty of the similarities of query-support pairs and performing uncertainty-aware optimization. Particularly, we exploit such uncertainty by converting observed similarities to probabilistic representations and incorporate them to the loss for more effective optimization. In order to jointly consider the similarities between a query and the prototypes in a support set, a graph-based model is utilized to estimate the uncertainty of the pairs. Extensive experiments show our proposed method brings significant improvements on top of a strong baseline and achieves the state-of-the-art performance.

Occluded person re-identification (ReID) aims to match person images with occlusion. It is fundamentally challenging because of the serious occlusion which aggravates the misalignment problem between images. At the cost of incorporating a pose estimator, many works introduce pose information to alleviate the misalignment in both training and testing. To achieve high accuracy while preserving low inference complexity, we propose a network named Pose-Guided Feature Learning with Knowledge Distillation (PGFL-KD), where the pose information is exploited to regularize the learning of semantics aligned features but is discarded in testing. PGFL-KD consists of a main branch (MB), and two pose-guided branches, e.g., a foreground-enhanced branch (FEB), and a body part semantics aligned branch (SAB). The FEB intends to emphasise the features of visible body parts while excluding the interference of obstructions and background (e.g., foreground feature alignment). The SAB encourages different channel groups to focus on different body parts to have body part semantics aligned representation. To get rid of the dependency on pose information when testing, we regularize the MB to learn the merits of the FEB and SAB through knowledge distillation and interaction-based training. Extensive experiments on occluded, partial, and holistic ReID tasks show the effectiveness of our proposed network.

Unsupervised domain adaptive classifcation intends to improve the classifcation performance on unlabeled target domain. To alleviate the adverse effect of domain shift, many approaches align the source and target domains in the feature space. However, a feature is usually taken as a whole for alignment without explicitly making domain alignment proactively serve the classifcation task, leading to sub-optimal solution. In this paper, we propose an effective Task-oriented Alignment (ToAlign) for unsupervised domain adaptation (UDA). We study what features should be aligned across domains and propose to make the domain alignment proactively serve classifcation by performing feature decomposition and alignment under the guidance of the prior knowledge induced from the classifcation task itself. Particularly, we explicitly decompose a feature in the source domain into a task-related/discriminative feature that should be aligned, and a task-irrelevant feature that should be avoided/ignored, based on the classifcation meta-knowledge. Extensive experimental results on various benchmarks (e.g., Offce-Home, Visda-2017, and DomainNet) under different domain adaptation settings demonstrate the effectiveness of ToAlign which helps achieve the state-of-the-art performance. The code is publicly available at https://github.com/microsoft/UDA.

Learning good feature representations is important for deep reinforcement learning (RL). However, with limited experience, RL often suffers from data inefficiency for training. For un-experienced or less-experienced trajectories (i.e., state-action sequences), the lack of data limits the use of them for better feature learning. In this work, we propose a novel method, dubbed PlayVirtual, which augments cycle-consistent virtual trajectories to enhance the data efficiency for RL feature representation learning. Specifically, PlayVirtual predicts future states in a latent space based on the current state and action by a dynamics model and then predicts the previous states by a backward dynamics model, which forms a trajectory cycle. Based on this, we augment the actions to generate a large amount of virtual state-action trajectories. Being free of groudtruth state supervision, we enforce a trajectory to meet the cycle consistency constraint, which can significantly enhance the data efficiency. We validate the effectiveness of our designs on the Atari and DeepMind Control Suite benchmarks. Our method achieves the state-of-the-art performance on both benchmarks. Our code is available at https://github.com/microsoft/Playvirtual.

Deep deterministic policy gradient (DDPG) has been proved to be a successful reinforcement learning (RL) algorithm for continuous control tasks. However, DDPG still suffers from data insufficiency and training inefficiency, especially, in computationally complex environments. In this article, we propose asynchronous episodic DDPG (AE-DDPG), as an expansion of DDPG, which can achieve more effective learning with less training time required. First, we design a modified scheme for data collection in an asynchronous fashion. Generally, for asynchronous RL algorithms, sample efficiency or/and training stability diminish as the degree of parallelism increases. We consider this problem from the perspectives of both data generation and data utilization. In detail, we redesign experience replay by introducing the idea of episodic control so that the agent can latch on good trajectories rapidly. In addition, we also inject a new type of noise in action space to enrich the exploration behaviors. Experiments demonstrate that our AE-DDPG achieves higher rewards and requires less time consumption than most popular RL algorithms in learning to run task which has a computationally complex environment. Not limited to the control tasks in the computationally complex environments, AE-DDPG also achieves higher rewards and two-fold to four-fold improvement in sample efficiency on average compared with other variants of DDPG in MuJoCo environments. Furthermore, we verify the effectiveness of each proposed technique component through abundant ablation study.

Feature Normalization (FN) is an important technique to help neural network training, which typically normalizes features across spatial dimensions. Most previous image inpainting methods apply FN in their networks without considering the impact of the corrupted regions of the input image on normalization, e.g. mean and variance shifts. In this work, we show that the mean and variance shifts caused by full-spatial FN limit the image inpainting network training and we propose a spatial region-wise normalization named Region Normalization (RN) to overcome the limitation. RN divides spatial pixels into different regions according to the input mask, and computes the mean and variance in each region for normalization. We develop two kinds of RN for our image inpainting network: (1) Basic RN (RN-B), which normalizes pixels from the corrupted and uncorrupted regions separately based on the original inpainting mask to solve the mean and variance shift problem; (2) Learnable RN (RN-L), which automatically detects potentially corrupted and uncorrupted regions for separate normalization, and performs global affine transformation to enhance their fusion. We apply RN-B in the early layers and RN-L in the latter layers of the network respectively. Experiments show that our method outperforms current state-of-the-art methods quantitatively and qualitatively. We further generalize RN to other inpainting networks and achieve consistent performance improvements.

Video-based person re-identification (reID) aims at matching the same person across video clips. It is a challenging task due to the existence of redundancy among frames, newly revealed appearance, occlusion, and motion blurs. In this paper, we propose an attentive feature aggregation module, namely Multi-Granularity Reference-aided Attentive Feature Aggregation (MG-RAFA), to delicately aggregate spatio-temporal features into a discriminative video-level feature representation. In order to determine the contribution/importance of a spatial-temporal feature node, we propose to learn the attention from a global view with convolutional operations. Specifically, we stack its relations, \ieno, pairwise correlations with respect to a representative set of reference feature nodes (S-RFNs) that represents global video information, together with the feature itself to infer the attention. Moreover, to exploit the semantics of different levels, we propose to learn multi-granularity attentions based on the relations captured at different granularities. Extensive ablation studies demonstrate the effectiveness of our attentive feature aggregation module MG-RAFA. Our framework achieves the state-of-the-art performance on three benchmark datasets.

For person re-identification (re-id), attention mechanisms have become attractive as they aim at strengthening discriminative features and suppressing irrelevant ones, which matches well the key of re-id, i.e., discriminative feature learning. Previous approaches typically learn attention using local convolutions, ignoring the mining of knowledge from global structure patterns. Intuitively, the affinities among spatial positions/nodes in the feature map provide clustering-like information and are helpful for inferring semantics and thus attention, especially for person images where the feasible human poses are constrained. In this work, we propose an effective Relation-Aware Global Attention (RGA) module which captures the global structural information for better attention learning. Specifically, for each feature position, in order to compactly grasp the structural information of global scope and local appearance information, we propose to stack the relations, i.e., its pairwise correlations/affinities with all the feature positions (e.g., in raster scan order), and the feature itself together to learn the attention with a shallow convolutional model. Extensive ablation studies demonstrate that our RGA can significantly enhance the feature representation power and help achieve the state-of-the-art performance on several popular benchmarks. The source code is available at https://github.com/microsoft/Relation-Aware-Global-Attention-Networks.

We propose a densely semantically aligned person re-identification (re-ID) framework. It fundamentally addresses the body misalignment problem caused by pose/viewpoint variations, imperfect person detection, occlusion, etc.. By leveraging the estimation of the dense semantics of a person image, we construct a set of densely semantically aligned part images (DSAP-images), where the same spatial positions have the same semantics across different person images. We design a two-stream network that consists of a main full image stream (MF-Stream) and a densely semantically-aligned guiding stream (DSAG-Stream). The DSAG-Stream, with the DSAP-images as input, acts as a regulator to guide the MF-Stream to learn densely semantically aligned features from the original image. In the inference, the DSAG-Stream is discarded and only the MF-Stream is needed, which makes the inference system computationally efficient and robust. To our best knowledge, we are the first to make use of fine grained semantics for addressing misalignment problems for re-ID. Our method achieves rank-1 accuracy of 78.9% (new protocol) on the CUHK03 dataset, 90.4% on the CUHK01 dataset, and 95.7% on the Market1501 dataset, outperforming state-of-the-art methods.

Automatic color enhancement are aimed to automaticly and adaptively adjust photos to expected styles and tones. For current learned methods in this field, global harmonious perception and local details are hard to be well-considered in a single model simultaneously. To address this problem, we propose a coarse-to-fine framework with non-local attention for color enhancement in this paper. Within our framework, we propose to divide enhancement process into channel-wise enhancement and pixel-wise refinement performed by two cascaded Convolutional Neural Networks (CNNs). In channel-wise enhancement, our model predicts a global linear mapping for RGB channels of input images to perform global style adjustment. In pixel-wise refinement, we learn a refining mapping using residual learning for local adjustment. Further, we adopt a non-local attention block to capture the long-range dependencies from global information for subsequent fine-grained local refinement. We evaluate our proposed framework on the commonly using benchmark and conduct sufficient experiments to demonstrate each technical component within it.

Tile-based 360-degree video (360 video) streaming, employed with adaptive bitrate (ABR) algorithms, is a promising approach to offer high video quality of experience (QoE) within limited network bandwidth. Existing ABR algorithms, however, fail to achieve optimal performance in real-world fluctuated network conditions as they heavily rely on unbiased bandwidth predictions. Recently, reinforcement learning (RL) has shown promising potential in generating better ABR algorithms in 2D video streaming. However, unlike existed work in 2D video streaming, directly applying RL in the tile-based 360 video streaming is infeasible due to the resulting exponential decision space. To overcome these limitations, we propose in this paper 360SRL, an improved ABR algorithm employing Sequential RL (360SRL). Firstly, we reduce the decision space of 360SRL from exponential to linear by introducing a sequential ABR decision structure, thus making it feasible to be employed with RL. Secondly, instead of relying on accurate bandwidth predictions, 360SRL learns to make ABR decisions solely through observations of the resulting QoE performance of past decisions. Finally, we compare 360SRL to state-of-the-art ABR algorithms using trace-driven experiments. The experiment results demonstrate that 360SRL outperforms state-of-the-art algorithms with around 12% improvement in average QoE.

In this paper, we propose a learned scalable/progressive image compression scheme based on deep neural networks (DNN), named Bidirectional Context Disentanglement Network (BCD-Net). For learning hierarchical representations, we first adopt bit-plane decomposition to decompose the information coarsely before the deep-learning-based transformation. However, the information carried by different bit-planes is not only unequal in entropy but also of different importance for reconstruction. We thus take the hidden features corresponding to different bit-planes as the context and design a network topology with bidirectional flows to disentangle the contextual information for more effective compressed representations. Our proposed scheme enables us to obtain the compressed codes with scalable rates via a one-pass encoding-decoding. Experiment results demonstrate that our proposed model outperforms the state-of-the-art DNN-based scalable image compression methods in both PSNR and MS-SSIM metrics. In addition, our proposed model achieves better performance in MS-SSIM metric than conventional scalable image codecs. Effectiveness of our technical components is also verified through sufficient ablation experiments.

Scalable image compression allows reconstructing complete images through partially decoding. It plays an important role for image transmission and storage. In this paper, we study the problem of feature decorrelation for Deep Neural Network (DNN) based image codec. Inspired by self-attention mechanism [1], we design a transformer-based decorrelation unit (DU) and adopt it in our scalable image compression framework to reduce the redundancy of feature representations at different levels. Experimental results demonstrate that proposed framework outperforms the state-of-the-art DNN-based scalable image codec and conventional scalable image codecs in terms of MS-SSIM. We also conduct ablation experiments which explicitly verify the effectiveness of decorrelation unit in our scheme.

Automating teleoperated robots is an essential task for transforming human-robot interaction design into practical applications. In this paper, we present a Collaborative Vision-based Sensing Scheme (CVSS) for automating mobile robotic furniture in the household environment. Using multiple cameras to perceive users' spatial information and capture their body postures respectively, our sensing scheme can provide formerly teleoperated robots with sufficient situational awareness of the users' surroundings and enable them to understand the interactive willingness of humans. As an application instance, we introduce the design of a furniture-type robot, called Automan, whose prototype is a teleoperated mechanical ottoman reported in [1]. Utilizing CVSS, we enable Automan the similar functions as teleoperated ottoman to offer and withdraw services for humans. To evaluate our automation method, we conducted the subjective experiments with 20 participants to verify the effectiveness of it in comparison with the teleoperated ottomans in terms of interactive experience. And the result of paired samples t test indicates that the participants can't significantly distinguish whether the interactive ottoman is autonomous or teleoperated (p≫0.05). Furthermore, we also explored and analyzed users' satisfaction for different behavior styles between autonomous and teleoperated ottomans.