Lixin Duan

Yahao Liu, Jinhong Deng, Jiale Tao et al.

Existing works typically treat cross-domain semantic segmentation (CDSS) as a data distribution mismatch problem and focus on aligning the marginal distribution or conditional distribution. However, the label shift issue is unfortunately overlooked, which actually commonly exists in the CDSS task, and often causes a classifier bias in the learnt model. In this paper, we give an in-depth analysis and show that the damage of label shift can be overcome by aligning the data conditional distribution and correcting the posterior probability. To this end, we propose a novel approach to undo the damage of the label shift problem in CDSS. In implementation, we adopt class-level feature alignment for conditional distribution alignment, as well as two simple yet effective methods to rectify the classifier bias from source to target by remolding the classifier predictions. We conduct extensive experiments on the benchmark datasets of urban scenes, including GTA5 to Cityscapes and SYNTHIA to Cityscapes, where our proposed approach outperforms previous methods by a large margin. For instance, our model equipped with a self-training strategy reaches 59.3% mIoU on GTA5 to Cityscapes, pushing to a new state-of-the-art. The code will be available at https://github.com/manmanjun/Undoing UDA.

Guowei Xu, Jiale Tao, Wen Li et al.

In the realm of stochastic human motion prediction (SHMP), researchers have often turned to generative models like GANS, VAEs and diffusion models. However, most previous approaches have struggled to accurately predict motions that are both realistic and coherent with past motion due to a lack of guidance on the latent distribution. In this paper, we introduce Semantic Latent Directions (SLD) as a solution to this challenge, aiming to constrain the latent space to learn meaningful motion semantics and enhance the accuracy of SHMP. SLD defines a series of orthogonal latent directions and represents the hypothesis of future motion as a linear combination of these directions. By creating such an information bottleneck, SLD excels in capturing meaningful motion semantics, thereby improving the precision of motion predictions. Moreover, SLD offers controllable prediction capabilities by adjusting the coefficients of the latent directions during the inference phase. Expanding on SLD, we introduce a set of motion queries to enhance the diversity of predictions. By aligning these motion queries with the SLD space, SLD is further promoted to more accurate and coherent motion predictions. Through extensive experiments conducted on widely used benchmarks, we showcase the superiority of our method in accurately predicting motions while maintaining a balance of realism and diversity. Our code and pretrained models are available at https://github.com/GuoweiXu368/SLD-HMP.

Fanyue Wei, Wei Zeng, Zhenyang Li et al.

Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remarkable results have been achieved using diffusion-based generation models, the visual structure and details of the object are often unexpectedly changed during the diffusion process. One major reason is that these diffusion-based approaches typically adopt a simple reconstruction objective during training, which can hardly enforce appropriate structural consistency between the generated and the reference images. To this end, in this paper, we design a novel reinforcement learning framework by utilizing the deterministic policy gradient method for personalized text-to-image generation, with which various objectives, differential or even non-differential, can be easily incorporated to supervise the diffusion models to improve the quality of the generated images. Experimental results on personalized text-to-image generation benchmark datasets demonstrate that our proposed approach outperforms existing state-of-the-art methods by a large margin on visual fidelity while maintaining text-alignment. Our code is available at: \url{https://github.com/wfanyue/DPG-T2I-Personalization}.

Yan Zhang, Changyu Li, Ivor W. Tsang et al.

Cold-start issues have been more and more challenging for providing accurate recommendations with the fast increase of users and items. Most existing approaches attempt to solve the intractable problems via content-aware recommendations based on auxiliary information and/or cross-domain recommendations with transfer learning. Their performances are often constrained by the extremely sparse user-item interactions, unavailable side information, or very limited domain-shared users. Recently, meta-learners with meta-augmentation by adding noises to labels have been proven to be effective to avoid overfitting and shown good performance on new tasks. Motivated by the idea of meta-augmentation, in this paper, by treating a user's preference over items as a task, we propose a so-called Diverse Preference Augmentation framework with multiple source domains based on meta-learning (referred to as MetaDPA) to i) generate diverse ratings in a new domain of interest (known as target domain) to handle overfitting on the case of sparse interactions, and to ii) learn a preference model in the target domain via a meta-learning scheme to alleviate cold-start issues. Specifically, we first conduct multi-source domain adaptation by dual conditional variational autoencoders and impose a Multi-domain InfoMax (MDI) constraint on the latent representations to learn domain-shared and domain-specific preference properties. To avoid overfitting, we add a Mutually-Exclusive (ME) constraint on the output of decoders to generate diverse ratings given content data. Finally, these generated diverse ratings and the original ratings are introduced into the meta-training procedure to learn a preference meta-learner, which produces good generalization ability on cold-start recommendation tasks. Experiments on real-world datasets show our proposed MetaDPA clearly outperforms the current state-of-the-art baselines.

Jiale Tao, Biao Wang, Borun Xu et al.

Given a source image and a driving video depicting the same object type, the motion transfer task aims to generate a video by learning the motion from the driving video while preserving the appearance from the source image. In this paper, we propose a novel structure-aware motion modeling approach, the deformable anchor model (DAM), which can automatically discover the motion structure of arbitrary objects without leveraging their prior structure information. Specifically, inspired by the known deformable part model (DPM), our DAM introduces two types of anchors or keypoints: i) a number of motion anchors that capture both appearance and motion information from the source image and driving video; ii) a latent root anchor, which is linked to the motion anchors to facilitate better learning of the representations of the object structure information. Moreover, DAM can be further extended to a hierarchical version through the introduction of additional latent anchors to model more complicated structures. By regularizing motion anchors with latent anchor(s), DAM enforces the correspondences between them to ensure the structural information is well captured and preserved. Moreover, DAM can be learned effectively in an unsupervised manner. We validate our proposed DAM for motion transfer on different benchmark datasets. Extensive experiments clearly demonstrate that DAM achieves superior performance relative to existing state-of-the-art methods.

Anqi Zhao, Tong Chu, Yahao Liu et al.

In this work, we study the black-box targeted attack problem from the model discrepancy perspective. On the theoretical side, we present a generalization error bound for black-box targeted attacks, which gives a rigorous theoretical analysis for guaranteeing the success of the attack. We reveal that the attack error on a target model mainly depends on empirical attack error on the substitute model and the maximum model discrepancy among substitute models. On the algorithmic side, we derive a new algorithm for black-box targeted attacks based on our theoretical analysis, in which we additionally minimize the maximum model discrepancy(M3D) of the substitute models when training the generator to generate adversarial examples. In this way, our model is capable of crafting highly transferable adversarial examples that are robust to the model variation, thus improving the success rate for attacking the black-box model. We conduct extensive experiments on the ImageNet dataset with different classification models, and our proposed approach outperforms existing state-of-the-art methods by a significant margin. Our codes will be released.

Ye Huang, Di Kang, Shenghua Gao et al.

Existing pyramid-based upsamplers (e.g. SemanticFPN), although efficient, usually produce less accurate results compared to dilation-based models when using the same backbone. This is partially caused by the contaminated high-level features since they are fused and fine-tuned with noisy low-level features on limited data. To address this issue, we propose to use powerful pre-trained high-level features as guidance (HFG) so that the upsampler can produce robust results. Specifically, \emph{only} the high-level features from the backbone are used to train the class tokens, which are then reused by the upsampler for classification, guiding the upsampler features to more discriminative backbone features. One crucial design of the HFG is to protect the high-level features from being contaminated by using proper stop-gradient operations so that the backbone does not update according to the noisy gradient from the upsampler. To push the upper limit of HFG, we introduce a context augmentation encoder (CAE) that can efficiently and effectively operate on the low-resolution high-level feature, resulting in improved representation and thus better guidance. We named our complete solution as the High-Level Features Guided Decoder (HFGD). We evaluate the proposed HFGD on three benchmarks: Pascal Context, COCOStuff164k, and Cityscapes. HFGD achieves state-of-the-art results among methods that do not use extra training data, demonstrating its effectiveness and generalization ability.

Jinhong Deng, Xiaoyue Zhang, Wen Li et al.

Detection transformers like DETR have recently shown promising performance on many object detection tasks, but the generalization ability of those methods is still quite challenging for cross-domain adaptation scenarios. To address the cross-domain issue, a straightforward way is to perform token alignment with adversarial training in transformers. However, its performance is often unsatisfactory as the tokens in detection transformers are quite diverse and represent different spatial and semantic information. In this paper, we propose a new method called Spatial-aware and Semantic-aware Token Alignment (SSTA) for cross-domain detection transformers. In particular, we take advantage of the characteristics of cross-attention as used in detection transformer and propose the spatial-aware token alignment (SpaTA) and the semantic-aware token alignment (SemTA) strategies to guide the token alignment across domains. For spatial-aware token alignment, we can extract the information from the cross-attention map (CAM) to align the distribution of tokens according to their attention to object queries. For semantic-aware token alignment, we inject the category information into the cross-attention map and construct domain embedding to guide the learning of a multi-class discriminator so as to model the category relationship and achieve category-level token alignment during the entire adaptation process. We conduct extensive experiments on several widely-used benchmarks, and the results clearly show the effectiveness of our proposed method over existing state-of-the-art baselines.

Jiale Tao, Biao Wang, Tiezheng Ge et al.

Image animation aims to animate a source image by using motion learned from a driving video. Current state-of-the-art methods typically use convolutional neural networks (CNNs) to predict motion information, such as motion keypoints and corresponding local transformations. However, these CNN based methods do not explicitly model the interactions between motions; as a result, the important underlying motion relationship may be neglected, which can potentially lead to noticeable artifacts being produced in the generated animation video. To this end, we propose a new method, the motion transformer, which is the first attempt to build a motion estimator based on a vision transformer. More specifically, we introduce two types of tokens in our proposed method: i) image tokens formed from patch features and corresponding position encoding; and ii) motion tokens encoded with motion information. Both types of tokens are sent into vision transformers to promote underlying interactions between them through multi-head self attention blocks. By adopting this process, the motion information can be better learned to boost the model performance. The final embedded motion tokens are then used to predict the corresponding motion keypoints and local transformations. Extensive experiments on benchmark datasets show that our proposed method achieves promising results to the state-of-the-art baselines. Our source code will be public available.

Borun Xu, Biao Wang, Jinhong Deng et al.

Motion transfer aims to transfer the motion of a driving video to a source image. When there are considerable differences between object in the driving video and that in the source image, traditional single domain motion transfer approaches often produce notable artifacts; for example, the synthesized image may fail to preserve the human shape of the source image (cf . Fig. 1 (a)). To address this issue, in this work, we propose a Motion and Appearance Adaptation (MAA) approach for cross-domain motion transfer, in which we regularize the object in the synthesized image to capture the motion of the object in the driving frame, while still preserving the shape and appearance of the object in the source image. On one hand, considering the object shapes of the synthesized image and the driving frame might be different, we design a shape-invariant motion adaptation module that enforces the consistency of the angles of object parts in two images to capture the motion information. On the other hand, we introduce a structure-guided appearance consistency module designed to regularize the similarity between the corresponding patches of the synthesized image and the source image without affecting the learned motion in the synthesized image. Our proposed MAA model can be trained in an end-to-end manner with a cyclic reconstruction loss, and ultimately produces a satisfactory motion transfer result (cf . Fig. 1 (b)). We conduct extensive experiments on human dancing dataset Mixamo-Video to Fashion-Video and human face dataset Vox-Celeb to Cufs; on both of these, our MAA model outperforms existing methods both quantitatively and qualitatively.

Ye Huang, Di Kang, Liang Chen et al.

Semantic segmentation has recently achieved notable advances by exploiting "class-level" contextual information during learning. However, these approaches simply concatenate class-level information to pixel features to boost the pixel representation learning, which cannot fully utilize intra-class and inter-class contextual information. Moreover, these approaches learn soft class centers based on coarse mask prediction, which is prone to error accumulation. To better exploit class level information, we propose a universal Class-Aware Regularization (CAR) approach to optimize the intra-class variance and inter-class distance during feature learning, motivated by the fact that humans can recognize an object by itself no matter which other objects it appears with. Moreover, we design a dedicated decoder for CAR (CARD), which consists of a novel spatial token mixer and an upsampling module, to maximize its gain for existing baselines while being highly efficient in terms of computational cost. Specifically, CAR consists of three novel loss functions. The first loss function encourages more compact class representations within each class, the second directly maximizes the distance between different class centers, and the third further pushes the distance between inter-class centers and pixels. Furthermore, the class center in our approach is directly generated from ground truth instead of from the error-prone coarse prediction. CAR can be directly applied to most existing segmentation models during training, and can largely improve their accuracy at no additional inference overhead. Extensive experiments and ablation studies conducted on multiple benchmark datasets demonstrate that the proposed CAR can boost the accuracy of all baseline models by up to 2.23% mIOU with superior generalization ability. CARD outperforms SOTA approaches on multiple benchmarks with a highly efficient architecture.

Junde Wu, Huihui Fang, Hoayi Xiong et al.

On the medical images, many of the tissues/lesions may be ambiguous. That is why the medical segmentation is typically annotated by a group of clinical experts to mitigate the personal bias. However, this clinical routine also brings new challenges to the application of machine learning algorithms. Without a definite ground-truth, it will be difficult to train and evaluate the deep learning models. When the annotations are collected from different graders, a common choice is majority vote. However such a strategy ignores the difference between the grader expertness. In this paper, we consider the task of predicting the segmentation with the calibrated inter-observer uncertainty. We note that in clinical practice, the medical image segmentation is usually used to assist the disease diagnosis. Inspired by this observation, we propose diagnosis-first principle, which is to take disease diagnosis as the criterion to calibrate the inter-observer segmentation uncertainty. Following this idea, a framework named Diagnosis First segmentation Framework (DiFF) is proposed to estimate diagnosis-first segmentation from the raw images.Specifically, DiFF will first learn to fuse the multi-rater segmentation labels to a single ground-truth which could maximize the disease diagnosis performance. We dubbed the fused ground-truth as Diagnosis First Ground-truth (DF-GT).Then, we further propose Take and Give Modelto segment DF-GT from the raw image. We verify the effectiveness of DiFF on three different medical segmentation tasks: OD/OC segmentation on fundus images, thyroid nodule segmentation on ultrasound images, and skin lesion segmentation on dermoscopic images. Experimental results show that the proposed DiFF is able to significantly facilitate the corresponding disease diagnosis, which outperforms previous state-of-the-art multi-rater learning methods.

Junde Wu, Huihui Fang, Yehui Yang et al.

In medical image segmentation, it is often necessary to collect opinions from multiple experts to make the final decision. This clinical routine helps to mitigate individual bias. But when data is multiply annotated, standard deep learning models are often not applicable. In this paper, we propose a novel neural network framework, called Multi-Rater Prism (MrPrism) to learn the medical image segmentation from multiple labels. Inspired by the iterative half-quadratic optimization, the proposed MrPrism will combine the multi-rater confidences assignment task and calibrated segmentation task in a recurrent manner. In this recurrent process, MrPrism can learn inter-observer variability taking into account the image semantic properties, and finally converges to a self-calibrated segmentation result reflecting the inter-observer agreement. Specifically, we propose Converging Prism (ConP) and Diverging Prism (DivP) to process the two tasks iteratively. ConP learns calibrated segmentation based on the multi-rater confidence maps estimated by DivP. DivP generates multi-rater confidence maps based on the segmentation masks estimated by ConP. The experimental results show that by recurrently running ConP and DivP, the two tasks can achieve mutual improvement. The final converged segmentation result of MrPrism outperforms state-of-the-art (SOTA) strategies on a wide range of medical image segmentation tasks.

Fanyue Wei, Biao Wang, Tiezheng Ge et al.

The goal of video highlight detection is to select the most attractive segments from a long video to depict the most interesting parts of the video. Existing methods typically focus on modeling relationship between different video segments in order to learning a model that can assign highlight scores to these segments; however, these approaches do not explicitly consider the contextual dependency within individual segments. To this end, we propose to learn pixel-level distinctions to improve the video highlight detection. This pixel-level distinction indicates whether or not each pixel in one video belongs to an interesting section. The advantages of modeling such fine-level distinctions are two-fold. First, it allows us to exploit the temporal and spatial relations of the content in one video, since the distinction of a pixel in one frame is highly dependent on both the content before this frame and the content around this pixel in this frame. Second, learning the pixel-level distinction also gives a good explanation to the video highlight task regarding what contents in a highlight segment will be attractive to people. We design an encoder-decoder network to estimate the pixel-level distinction, in which we leverage the 3D convolutional neural networks to exploit the temporal context information, and further take advantage of the visual saliency to model the spatial distinction. State-of-the-art performance on three public benchmarks clearly validates the effectiveness of our framework for video highlight detection.

Jiale Tao, Shuhang Gu, Wen Li et al.

Unsupervised face animation aims to generate a human face video based on the appearance of a source image, mimicking the motion from a driving video. Existing methods typically adopted a prior-based motion model (e.g., the local affine motion model or the local thin-plate-spline motion model). While it is able to capture the coarse facial motion, artifacts can often be observed around the tiny motion in local areas (e.g., lips and eyes), due to the limited ability of these methods to model the finer facial motions. In this work, we design a new unsupervised face animation approach to learn simultaneously the coarse and finer motions. In particular, while exploiting the local affine motion model to learn the global coarse facial motion, we design a novel motion refinement module to compensate for the local affine motion model for modeling finer face motions in local areas. The motion refinement is learned from the dense correlation between the source and driving images. Specifically, we first construct a structure correlation volume based on the keypoint features of the source and driving images. Then, we train a model to generate the tiny facial motions iteratively from low to high resolution. The learned motion refinements are combined with the coarse motion to generate the new image. Extensive experiments on widely used benchmarks demonstrate that our method achieves the best results among state-of-the-art baselines.

Penglin Dai, Zijie Zhou, Xincao Xu et al.

Deploying neural networks on microcontroller units (MCUs) is critical for edge intelligence but remains challenging due to tight memory, storage, and computation constraints. Existing approaches, such as model compression and hardware-aware neural architecture search (HW-NAS), often depend on proxy metrics, incur high search cost, and do not fully bridge the gap between architecture design and verified deployment. This paper presents AutoMCU, a feasibility-first large language model (LLM)-based multi-agent system for automated neural network customization under MCU constraints. Given natural-language task requirements and hardware specifications, AutoMCU iteratively generates structured architecture candidates, filters infeasible designs through vendor toolchain feedback before training, evaluates feasible models under a controlled protocol, and verifies deployability through backend-grounded deployment analysis. AutoMCU includes two key mechanisms: 1) hardware-in-the-loop architecture generation for early elimination of undeployable candidates under RAM and Flash constraints, and 2) state-isolated multi-agent scheduling for stable coordination of proposal, training, evaluation, and deployment stages. Experiments on CIFAR-10 and CIFAR-100 under strict MCU constraints show that AutoMCU achieves competitive accuracy while reducing customization time to about 1--2 hours, compared with hundreds of GPU hours for representative MCU-oriented HW-NAS baselines. Comparisons with ColabNAS and the LLM-based NAS method GENIUS on NAS-Bench-201 further demonstrate the effectiveness and stability of AutoMCU. Real-device deployments on multiple STM32 microcontrollers validate its practical applicability to MCU-scale edge intelligence.

Penglin Dai, Fulian Li, Xincao Xu et al.

Federated Learning (FL) has emerged as a promising paradigm for privacy-preserving distributed learning. However, existing FL methods face a fundamental challenge. Traditional averaging-based approaches suffer from parameter divergence under non-IID conditions, while personalized FL methods overfit to local data and fail to generalize to new clients (cold-start problem). Mixture-of-Experts naturally addresses this by routing heterogeneous data to specialized experts rather than forcing uniform aggregation. In this paper, we propose FedCoE, a Federated Coordinated dual-level mixture-of-Experts framework that effectively balances global generalization with local personalization. FedCoE maintains multiple independent global expert models on the server and employs a shared gating network to dynamically model client-expert correlations during aggregation, effectively mitigating expert drift and gating inconsistency. To address the cold-start challenge, we introduce an adaptive mechanism that enables new clients to immediately leverage the global expert pool without extensive local training. Extensive experiments demonstrate that FedCoE achieves 78.00% global accuracy and 89.32% personalized accuracy on average, outperforming the baseline by 8.82% and 29.19%, respectively. In cold-start scenarios, FedCoE delivers 77.27% accuracy without any local fine-tuning, outperforming baselines by over 12.54%.

Yuanqing Cai, Ziyi Huang, Minhao Liu et al.

Large language models (LLMs) are increasingly integrated into high-stakes decision-making. Inspired by the theory of \emph{inattentional blindness} in human cognition, we investigate whether LLMs, trained on human-preferred corpora that embed attentional biases, exhibit a similar limitation: \emph{failing to attend to subtle yet important contextual cues under explicit task instructions}. To evaluate this, we introduce the task of \textbf{explicit-implicit reasoning} and present \textbf{MixRea}, a benchmark of 2,246 multiple-choice questions across 9 reasoning types with varying distributions of explicit and implicit information. Evaluation of 21 advanced LLMs shows that even the best-performing reasoning model (Gemini 2.5 Pro) achieves only 42.8\% consistency, revealing widespread inattentional blindness. To mitigate this, we propose \textbf{Potential Relation Completion Prompting (PRCP)}, a prompting method that improves reasoning by recovering overlooked causal relations. Further analysis shows that this limitation persists across diverse multi-source reasoning tasks, highlighting the need for more cognitively aligned models.

Yanqi Ge, Qiang Nie, Ye Huang et al.

One of the ultimate goals of representation learning is to achieve compactness within a class and well-separability between classes. Many outstanding metric-based and prototype-based methods following the Expectation-Maximization paradigm, have been proposed for this objective. However, they inevitably introduce biases into the learning process, particularly with long-tail distributed training data. In this paper, we reveal that the class prototype is not necessarily to be derived from training features and propose a novel perspective to use pre-defined class anchors serving as feature centroid to unidirectionally guide feature learning. However, the pre-defined anchors may have a large semantic distance from the pixel features, which prevents them from being directly applied. To address this issue and generate feature centroid independent from feature learning, a simple yet effective Semantic Anchor Regularization (SAR) is proposed. SAR ensures the interclass separability of semantic anchors in the semantic space by employing a classifier-aware auxiliary cross-entropy loss during training via disentanglement learning. By pulling the learned features to these semantic anchors, several advantages can be attained: 1) the intra-class compactness and naturally inter-class separability, 2) induced bias or errors from feature learning can be avoided, and 3) robustness to the long-tailed problem. The proposed SAR can be used in a plug-and-play manner in the existing models. Extensive experiments demonstrate that the SAR performs better than previous sophisticated prototype-based methods. The implementation is available at https://github.com/geyanqi/SAR.

Zhuo Chen, Fanyue Wei, Runze Xu et al.

Training-free image editing with large diffusion models has become practical, yet faithfully performing complex non-rigid edits (e.g., pose or shape changes) remains highly challenging. We identify a key underlying cause: attention collapse in existing attention sharing mechanisms, where either positional embeddings or semantic features dominate visual content retrieval, leading to over-editing or under-editing. To address this issue, we introduce SynPS, a method that Synergistically leverages Positional embeddings and Semantic information for faithful non-rigid image editing. We first propose an editing measurement that quantifies the required editing magnitude at each denoising step. Based on this measurement, we design an attention synergy pipeline that dynamically modulates the influence of positional embeddings, enabling SynPS to balance semantic modifications and fidelity preservation. By adaptively integrating positional and semantic cues, SynPS effectively avoids both over- and under-editing. Extensive experiments on public and newly curated benchmarks demonstrate the superior performance and faithfulness of our approach.

Linlong Fan, Ye Huang, Yanqi Ge et al.

Existing view-based methods excel at recognizing 3D objects from predefined viewpoints, but their exploration of recognition under arbitrary views is limited. This is a challenging and realistic setting because each object has different viewpoint positions and quantities, and their poses are not aligned. However, most view-based methods, which aggregate multiple view features to obtain a global feature representation, hard to address 3D object recognition under arbitrary views. Due to the unaligned inputs from arbitrary views, it is challenging to robustly aggregate features, leading to performance degradation. In this paper, we introduce a novel Part-aware Network (PANet), which is a part-based representation, to address these issues. This part-based representation aims to localize and understand different parts of 3D objects, such as airplane wings and tails. It has properties such as viewpoint invariance and rotation robustness, which give it an advantage in addressing the 3D object recognition problem under arbitrary views. Our results on benchmark datasets clearly demonstrate that our proposed method outperforms existing view-based aggregation baselines for the task of 3D object recognition under arbitrary views, even surpassing most fixed viewpoint methods.

Yuhang Yang, Jinhong Deng, Wen Li et al.

While vision-language models like CLIP have shown remarkable success in open-vocabulary tasks, their application is currently confined to image-level tasks, and they still struggle with dense predictions. Recent works often attribute such deficiency in dense predictions to the self-attention layers in the final block, and have achieved commendable results by modifying the original query-key attention to self-correlation attention, (e.g., query-query and key-key attention). However, these methods overlook the cross-correlation attention (query-key) properties, which capture the rich spatial correspondence. In this paper, we reveal that the cross-correlation of the self-attention in CLIP's non-final layers also exhibits localization properties. Therefore, we propose the Residual Cross-correlation Self-attention (RCS) module, which leverages the cross-correlation self-attention from intermediate layers to remold the attention in the final block. The RCS module effectively reorganizes spatial information, unleashing the localization potential within CLIP for dense vision-language inference. Furthermore, to enhance the focus on regions of the same categories and local consistency, we propose the Semantic Feedback Refinement (SFR) module, which utilizes semantic segmentation maps to further adjust the attention scores. By integrating these two strategies, our method, termed ResCLIP, can be easily incorporated into existing approaches as a plug-and-play module, significantly boosting their performance in dense vision-language inference. Extensive experiments across multiple standard benchmarks demonstrate that our method surpasses state-of-the-art training-free methods, validating the effectiveness of the proposed approach. Code is available at https://github.com/yvhangyang/ResCLIP.

Hengfu Yu, Jinhong Deng, Lixin Duan et al.

While Domain Adaptive Object Detection (DAOD) has made significant strides, most methods rely on unlabeled target data that is assumed to contain sufficient foreground instances. However, in many practical scenarios (e.g., wildlife monitoring, lesion detection), collecting target domain data with objects of interest is prohibitively costly, whereas background-only data is abundant. This common practical constraint introduces a significant technical challenge: the difficulty of achieving domain alignment when target instances are unavailable, forcing adaptation to rely solely on the target background information. We formulate this challenge as the novel problem of Instance-Free Domain Adaptive Object Detection. To tackle this, we propose the Relational and Structural Consistency Network (RSCN) which pioneers an alignment strategy based on background feature prototypes while simultaneously encouraging consistency in the relationship between the source foreground features and the background features within each domain, enabling robust adaptation even without target instances. To facilitate research, we further curate three specialized benchmarks, including simulative auto-driving detection, wildlife detection, and lung nodule detection. Extensive experiments show that RSCN significantly outperforms existing DAOD methods across all three benchmarks in the instance-free scenario. The code and benchmarks will be released soon.

Xiao Cao, Yuze Li, Youmin Zhang et al.

3D Gaussian Splatting (3DGS) has emerged as a prominent paradigm for 3D reconstruction and novel view synthesis. However, it remains vulnerable to severe artifacts when trained under sparse-view constraints. While recent methods attempt to rectify artifacts in rendered views using image diffusion models, they typically rely on multi-view self-attention to retrieve information from reference images. We observe that this mechanism often fails when the rendered novel views output by 3DGS are heavily corrupted: damaged query features lead to erroneous cross-view retrieval, resulting in inconsistent rendering refinement. To address this, we propose GeoQuery, a geometry-guided diffusion framework that integrates generative priors with explicit geometric cues via a novel Geometry-guided Cross-view Attention (GCA) mechanism. First, by leveraging predicted depth maps and camera poses, we construct a geometry-induced correspondence field to sample reference features, forming a geometry-aligned proxy query that replaces the corrupted rendering features. Furthermore, we design a new cross-view feature aggregation pipeline, in which we restrict the cross-view attention to a local window around each proxy query to effectively retrieve useful features while suppressing spurious matches. GeoQuery can be seamlessly integrated into existing diffusion-based pipelines, enabling robust reconstruction even under extreme view sparsity. Extensive experiments on sparse-view novel view synthesis and rendering artifact removal demonstrate the effectiveness of our approach.

Yahao Liu, Qin Wang, Lixin Duan et al.

Regression is fundamental in computer vision and is widely used in various tasks including age estimation, depth estimation, target localization, \etc However, real-world data often exhibits imbalanced distribution, making regression models perform poorly especially for target values with rare observations~(known as the imbalanced regression problem). In this paper, we reframe imbalanced regression as an imbalanced generalization problem. To tackle that, we look into the loss sharpness property for measuring the generalization ability of regression models in the observation space. Namely, given a certain perturbation on the model parameters, we check how model performance changes according to the loss values of different target observations. We propose a simple yet effective approach called Balanced Sharpness-Aware Minimization~(BSAM) to enforce the uniform generalization ability of regression models for the entire observation space. In particular, we start from the traditional sharpness-aware minimization and then introduce a novel targeted reweighting strategy to homogenize the generalization ability across the observation space, which guarantees a theoretical generalization bound. Extensive experiments on multiple vision regression tasks, including age and depth estimation, demonstrate that our BSAM method consistently outperforms existing approaches. The code is available \href{https://github.com/manmanjun/BSAM_for_Imbalanced_Regression}{here}.

Yifei Sun, Zhanghao Chen, Hao Zheng et al.

Chest X-Ray (CXR) imaging for pulmonary diagnosis raises significant challenges, primarily because bone structures can obscure critical details necessary for accurate diagnosis. Recent advances in deep learning, particularly with diffusion models, offer significant promise for effectively minimizing the visibility of bone structures in CXR images, thereby improving clarity and diagnostic accuracy. Nevertheless, existing diffusion-based methods for bone suppression in CXR imaging struggle to balance the complete suppression of bones with preserving local texture details. Additionally, their high computational demand and extended processing time hinder their practical use in clinical settings. To address these limitations, we introduce a Global-Local Latent Consistency Model (GL-LCM) architecture. This model combines lung segmentation, dual-path sampling, and global-local fusion, enabling fast high-resolution bone suppression in CXR images. To tackle potential boundary artifacts and detail blurring in local-path sampling, we further propose Local-Enhanced Guidance, which addresses these issues without additional training. Comprehensive experiments on a self-collected dataset SZCH-X-Rays, and the public dataset JSRT, reveal that our GL-LCM delivers superior bone suppression and remarkable computational efficiency, significantly outperforming several competitive methods. Our code is available at https://github.com/diaoquesang/GL-LCM.

Xinyang Zhou, Fanyue Wei, Lixin Duan et al.

Given a textual query along with a corresponding video, the objective of moment retrieval aims to localize the moments relevant to the query within the video. While commendable results have been demonstrated by existing transformer-based approaches, predicting the accurate temporal span of the target moment is still a major challenge. This paper reveals that a crucial reason stems from the spurious correlation between the text query and the moment context. Namely, the model makes predictions by overly associating queries with background frames rather than distinguishing target moments. To address this issue, we propose a dynamic learning approach for moment retrieval, where two strategies are designed to mitigate the spurious correlation. First, we introduce a novel video synthesis approach to construct a dynamic context for the queried moment, enabling the model to attend to the target moment of the corresponding query across dynamic backgrounds. Second, to alleviate the over-association with backgrounds, we enhance representations temporally by incorporating text-dynamics interaction, which encourages the model to align text with target moments through complementary dynamic representations. With the proposed method, our model significantly alleviates the spurious correlation issue in moment retrieval and establishes new state-of-the-art performance on two popular benchmarks, \ie, QVHighlights and Charades-STA. In addition, detailed ablation studies and evaluations across different architectures demonstrate the generalization and effectiveness of the proposed strategies. Our code will be publicly available.

Jinhong Deng, Wen Li, Yuhua Chen et al.

Cross-domain object detection is challenging, because object detection model is often vulnerable to data variance, especially to the considerable domain shift between two distinctive domains. In this paper, we propose a new Unbiased Mean Teacher (UMT) model for cross-domain object detection. We reveal that there often exists a considerable model bias for the simple mean teacher (MT) model in cross-domain scenarios, and eliminate the model bias with several simple yet highly effective strategies. In particular, for the teacher model, we propose a cross-domain distillation method for MT to maximally exploit the expertise of the teacher model. Moreover, for the student model, we alleviate its bias by augmenting training samples with pixel-level adaptation. Finally, for the teaching process, we employ an out-of-distribution estimation strategy to select samples that most fit the current model to further enhance the cross-domain distillation process. By tackling the model bias issue with these strategies, our UMT model achieves mAPs of 44.1%, 58.1%, 41.7%, and 43.1% on benchmark datasets Clipart1k, Watercolor2k, Foggy Cityscapes, and Cityscapes, respectively, which outperforms the existing state-of-the-art results in notable margins. Our implementation is available at https://github.com/kinredon/umt.

Yuan Qing, Naixing Wu, Shaohua Wan et al.

Unsupervised cross-domain action recognition aims at adapting the model trained on an existing labeled source domain to a new unlabeled target domain. Most existing methods solve the task by directly aligning the feature distributions of source and target domains. However, this would cause negative transfer during domain adaptation due to some negative training samples in both domains. In the source domain, some training samples are of low-relevance to target domain due to the difference in viewpoints, action styles, etc. In the target domain, there are some ambiguous training samples that can be easily classified as another type of action under the case of source domain. The problem of negative transfer has been explored in cross-domain object detection, while it remains under-explored in cross-domain action recognition. Therefore, we propose a Multi-modal Instance Refinement (MMIR) method to alleviate the negative transfer based on reinforcement learning. Specifically, a reinforcement learning agent is trained in both domains for every modality to refine the training data by selecting out negative samples from each domain. Our method finally outperforms several other state-of-the-art baselines in cross-domain action recognition on the benchmark EPIC-Kitchens dataset, which demonstrates the advantage of MMIR in reducing negative transfer.

Zhilin Liu, Ye Huang, Ting Xie et al.

Recent advances in Large Language Model (LLM)-based agents have shown remarkable progress in code generation. However, current agent methods mainly rely on text-output-based feedback (e.g. command-line outputs) for multi-round debugging and struggle in graphical user interface (GUI) that involve visual information. This is mainly due to two limitations: 1) GUI programs are event-driven, yet existing methods cannot simulate user interactions to trigger GUI element logic 2) GUI programs possess visual attributes, making it difficult for text-based approaches to assess whether the rendered interface meets user needs. To systematically address these challenges, we first introduce InteractGUI Bench, a novel benchmark comprising 984 commonly used real-world desktop GUI application tasks designed for fine-grained evaluation of both interaction logic and visual structure. Furthermore, we propose VF-Coder, a vision-feedback-based multi-agent system for debugging GUI code. By perceiving visual information and directly interacting with program interfaces, VF-Coder can identify potential logic and layout issues in a human-like manner. On InteractGUI Bench, our VF-Coder approach increases the success rate of Gemini-3-Flash from 21.68% to 28.29% and raises the visual score from 0.4284 to 0.5584, indicating the effectiveness of visual feedback in GUI debugging.

Xunsong Li, Pengzhan Sun, Yangcen Liu et al.

The interactions between human and objects are important for recognizing object-centric actions. Existing methods usually adopt a two-stage pipeline, where object proposals are first detected using a pretrained detector, and then are fed to an action recognition model for extracting video features and learning the object relations for action recognition. However, since the action prior is unknown in the object detection stage, important objects could be easily overlooked, leading to inferior action recognition performance. In this paper, we propose an end-to-end object-centric action recognition framework that simultaneously performs Detection And Interaction Reasoning in one stage. Particularly, after extracting video features with a base network, we create three modules for concurrent object detection and interaction reasoning. First, a Patch-based Object Decoder generates proposals from video patch tokens. Then, an Interactive Object Refining and Aggregation identifies important objects for action recognition, adjusts proposal scores based on position and appearance, and aggregates object-level info into a global video representation. Lastly, an Object Relation Modeling module encodes object relations. These three modules together with the video feature extractor can be trained jointly in an end-to-end fashion, thus avoiding the heavy reliance on an off-the-shelf object detector, and reducing the multi-stage training burden. We conduct experiments on two datasets, Something-Else and Ikea-Assembly, to evaluate the performance of our proposed approach on conventional, compositional, and few-shot action recognition tasks. Through in-depth experimental analysis, we show the crucial role of interactive objects in learning for action recognition, and we can outperform state-of-the-art methods on both datasets.

Ruizhi Zhang, Ye Huang, Yuangang Pan et al.

While Vision-Language Models (VLMs) have achieved remarkable progress in static visual understanding, their deployment in complex 3D embodied environments remains severely limited. Existing benchmarks suffer from four critical deficiencies: (1) passive perception tasks circumvent interactive dynamics; (2) simplified 2D environments fail to assess depth perception; (3) privileged state leakage bypasses genuine visual processing; and (4) human evaluation is prohibitively expensive and unscalable. We introduce PokeGym, a visually-driven long-horizon benchmark instantiated within Pokemon Legends: Z-A, a visually complex 3D open-world Role-Playing Game. PokeGym enforces strict code-level isolation: agents operate solely on raw RGB observations while an independent evaluator verifies success via memory scanning, ensuring pure vision-based decision-making and automated, scalable assessment. The benchmark comprises 30 tasks (30-220 steps) spanning navigation, interaction, and mixed scenarios, with three instruction granularities (Visual-Guided, Step-Guided, Goal-Only) to systematically deconstruct visual grounding, semantic reasoning, and autonomous exploration capabilities. Our evaluation reveals a key limitation of current VLMs: physical deadlock recovery, rather than high-level planning, constitutes the primary bottleneck, with deadlocks showing a strong negative correlation with task success. Furthermore, we uncover a metacognitive divergence: weaker models predominantly suffer from Unaware Deadlocks (oblivious to entrapment), whereas advanced models exhibit Aware Deadlocks (recognizing entrapment yet failing to recover). These findings highlight the need to integrate explicit spatial intuition into VLM architectures. The code and benchmark will be available on GitHub.

Zixi Liang, Guowei Xu, Haifeng Wu et al.

Learning-based methods have become increasingly popular in 3D indoor scene synthesis (ISS), showing superior performance over traditional optimization-based approaches. These learning-based methods typically model distributions on simple yet explicit scene representations using generative models. However, due to the oversimplified explicit representations that overlook detailed information and the lack of guidance from multimodal relationships within the scene, most learning-based methods struggle to generate indoor scenes with realistic object arrangements and styles. In this paper, we introduce a new method, Scene Implicit Neural Field (S-INF), for indoor scene synthesis, aiming to learn meaningful representations of multimodal relationships, to enhance the realism of indoor scene synthesis. S-INF assumes that the scene layout is often related to the object-detailed information. It disentangles the multimodal relationships into scene layout relationships and detailed object relationships, fusing them later through implicit neural fields (INFs). By learning specialized scene layout relationships and projecting them into S-INF, we achieve a realistic generation of scene layout. Additionally, S-INF captures dense and detailed object relationships through differentiable rendering, ensuring stylistic consistency across objects. Through extensive experiments on the benchmark 3D-FRONT dataset, we demonstrate that our method consistently achieves state-of-the-art performance under different types of ISS.

Hengfu Yu, Jinhong Deng, Wen Li et al.

Evaluating the performance of deep models in new scenarios has drawn increasing attention in recent years. However, while it is possible to collect data from new scenarios, the annotations are not always available. Existing DAOD methods often rely on validation or test sets on the target domain for model selection, which is impractical in real-world applications. In this paper, we propose a novel unsupervised model selection approach for domain adaptive object detection, which is able to select almost the optimal model for the target domain without using any target labels. Our approach is based on the flat minima principle, i,e., models located in the flat minima region in the parameter space usually exhibit excellent generalization ability. However, traditional methods require labeled data to evaluate how well a model is located in the flat minima region, which is unrealistic for the DAOD task. Therefore, we design a Detection Adaptation Score (DAS) approach to approximately measure the flat minima without using target labels. We show via a generalization bound that the flatness can be deemed as model variance, while the minima depend on the domain distribution distance for the DAOD task. Accordingly, we propose a Flatness Index Score (FIS) to assess the flatness by measuring the classification and localization fluctuation before and after perturbations of model parameters and a Prototypical Distance Ratio (PDR) score to seek the minima by measuring the transferability and discriminability of the models. In this way, the proposed DAS approach can effectively evaluate the model generalization ability on the target domain. We have conducted extensive experiments on various DAOD benchmarks and approaches, and the experimental results show that the proposed DAS correlates well with the performance of DAOD models and can be used as an effective tool for model selection after training.

Xikai Tang, Ye Huang, Guangqiang Yin et al.

We present VPNeXt, a new and simple model for the Plain Vision Transformer (ViT). Unlike the many related studies that share the same homogeneous paradigms, VPNeXt offers a fresh perspective on dense representation based on ViT. In more detail, the proposed VPNeXt addressed two concerns about the existing paradigm: (1) Is it necessary to use a complex Transformer Mask Decoder architecture to obtain good representations? (2) Does the Plain ViT really need to depend on the mock pyramid feature for upsampling? For (1), we investigated the potential underlying reasons that contributed to the effectiveness of the Transformer Decoder and introduced the Visual Context Replay (VCR) to achieve similar effects efficiently. For (2), we introduced the ViTUp module. This module fully utilizes the previously overlooked ViT real pyramid feature to achieve better upsampling results compared to the earlier mock pyramid feature. This represents the first instance of such functionality in the field of semantic segmentation for Plain ViT. We performed ablation studies on related modules to verify their effectiveness gradually. We conducted relevant comparative experiments and visualizations to show that VPNeXt achieved state-of-the-art performance with a simple and effective design. Moreover, the proposed VPNeXt significantly exceeded the long-established mIoU wall/barrier of the VOC2012 dataset, setting a new state-of-the-art by a large margin, which also stands as the largest improvement since 2015.

Yanqi Ge, Jiaqi Liu, Qingnan Fan et al.

In this work, we target the task of text-driven style transfer in the context of text-to-image (T2I) diffusion models. The main challenge is consistent structure preservation while enabling effective style transfer effects. The past approaches in this field directly concatenate the content and style prompts for a prompt-level style injection, leading to unavoidable structure distortions. In this work, we propose a novel solution to the text-driven style transfer task, namely, Adaptive Style Incorporation~(ASI), to achieve fine-grained feature-level style incorporation. It consists of the Siamese Cross-Attention~(SiCA) to decouple the single-track cross-attention to a dual-track structure to obtain separate content and style features, and the Adaptive Content-Style Blending (AdaBlending) module to couple the content and style information from a structure-consistent manner. Experimentally, our method exhibits much better performance in both structure preservation and stylized effects.

Guowei Xu, Yuxuan Bian, Ailing Zeng et al.

This paper introduces OmniMotion-X, a versatile multimodal framework for whole-body human motion generation, leveraging an autoregressive diffusion transformer in a unified sequence-to-sequence manner. OmniMotion-X efficiently supports diverse multimodal tasks, including text-to-motion, music-to-dance, speech-to-gesture, and global spatial-temporal control scenarios (e.g., motion prediction, in-betweening, completion, and joint/trajectory-guided synthesis), as well as flexible combinations of these tasks. Specifically, we propose the use of reference motion as a novel conditioning signal, substantially enhancing the consistency of generated content, style, and temporal dynamics crucial for realistic animations. To handle multimodal conflicts, we introduce a progressive weak-to-strong mixed-condition training strategy. To enable high-quality multimodal training, we construct OmniMoCap-X, the largest unified multimodal motion dataset to date, integrating 28 publicly available MoCap sources across 10 distinct tasks, standardized to the SMPL-X format at 30 fps. To ensure detailed and consistent annotations, we render sequences into videos and use GPT-4o to automatically generate structured and hierarchical captions, capturing both low-level actions and high-level semantics. Extensive experimental evaluations confirm that OmniMotion-X significantly surpasses existing methods, demonstrating state-of-the-art performance across multiple multimodal tasks and enabling the interactive generation of realistic, coherent, and controllable long-duration motions.

Xie Ting, Ye Huang, Zhilin Liu et al.

In real-world scenarios, pixel-level labeling is not always available. Sometimes, we need a semantic segmentation network, and even a visual encoder can have a high compatibility, and can be trained using various types of feedback beyond traditional labels, such as feedback that indicates the quality of the parsing results. To tackle this issue, we proposed RSS (Reward in Semantic Segmentation), the first practical application of reward-based reinforcement learning on pure semantic segmentation offered in two granular levels (pixel-level and image-level). RSS incorporates various novel technologies, such as progressive scale rewards (PSR) and pair-wise spatial difference (PSD), to ensure that the reward facilitates the convergence of the semantic segmentation network, especially under image-level rewards. Experiments and visualizations on benchmark datasets demonstrate that the proposed RSS can successfully ensure the convergence of the semantic segmentation network on two levels of rewards. Additionally, the RSS, which utilizes an image-level reward, outperforms existing weakly supervised methods that also rely solely on image-level signals during training.

Xiang Li, Mingsi Liu, Lixin Duan

Purpose: Automatic and accurate segmentation of fundus vessel images has become an essential prerequisite for computer-aided diagnosis of ophthalmic diseases such as diabetes mellitus. The task of high-precision retinal vessel segmentation still faces difficulties due to the low contrast between the branch ends of retinal vessels and the background, the long and thin vessel span, and the variable morphology of the optic disc and optic cup in fundus vessel images. Methods: We propose a more advanced U-shaped architecture for a hybrid Transformer and CNN: TransUNext, which integrates an Efficient Self-attention Mechanism into the encoder and decoder of U-Net to capture both local features and global dependencies with minimal computational overhead. Meanwhile, the Global Multi-Scale Fusion (GMSF) module is further introduced to upgrade skip-connections, fuse high-level semantic and low-level detailed information, and eliminate high- and low-level semantic differences. Inspired by ConvNeXt, TransNeXt Block is designed to optimize the computational complexity of each base block in U-Net and avoid the information loss caused by the compressed dimension when the information is converted between the feature spaces of different dimensions. Results: We evaluated the proposed method on four public datasets DRIVE, STARE, CHASE-DB1, and HRF. In the experimental results, the AUC (area under the ROC curve) values were 0.9867, 0.9869, 0.9910, and 0.9887, which exceeded the other state-of-the-art.

Yanqi Ge, Ye Huang, Wen Li et al.

We introduced SSR, which utilizes SAM (segment-anything) as a strong regularizer during training, to greatly enhance the robustness of the image encoder for handling various domains. Specifically, given the fact that SAM is pre-trained with a large number of images over the internet, which cover a diverse variety of domains, the feature encoding extracted by the SAM is obviously less dependent on specific domains when compared to the traditional ImageNet pre-trained image encoder. Meanwhile, the ImageNet pre-trained image encoder is still a mature choice of backbone for the semantic segmentation task, especially when the SAM is category-irrelevant. As a result, our SSR provides a simple yet highly effective design. It uses the ImageNet pre-trained image encoder as the backbone, and the intermediate feature of each stage (ie there are 4 stages in MiT-B5) is regularized by SAM during training. After extensive experimentation on GTA5$\rightarrow$Cityscapes, our SSR significantly improved performance over the baseline without introducing any extra inference overhead.

Borun Xu, Biao Wang, Jiale Tao et al.

Creative image animations are attractive in e-commerce applications, where motion transfer is one of the import ways to generate animations from static images. However, existing methods rarely transfer motion to objects other than human body or human face, and even fewer apply motion transfer in practical scenarios. In this work, we apply motion transfer on the Taobao product images in real e-commerce scenario to generate creative animations, which are more attractive than static images and they will bring more benefits. We animate the Taobao products of dolls, copper running horses and toy dinosaurs based on motion transfer method for demonstration.

Andrey Ignatov, Andres Romero, Heewon Kim et al.

Video super-resolution has recently become one of the most important mobile-related problems due to the rise of video communication and streaming services. While many solutions have been proposed for this task, the majority of them are too computationally expensive to run on portable devices with limited hardware resources. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based video super-resolution solutions that can achieve a real-time performance on mobile GPUs. The participants were provided with the REDS dataset and trained their models to do an efficient 4X video upscaling. The runtime of all models was evaluated on the OPPO Find X2 smartphone with the Snapdragon 865 SoC capable of accelerating floating-point networks on its Adreno GPU. The proposed solutions are fully compatible with any mobile GPU and can upscale videos to HD resolution at up to 80 FPS while demonstrating high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.

Yan Zhang, Ivor W. Tsang, Lixin Duan

Cold-start has being a critical issue in recommender systems with the explosion of data in e-commerce. Most existing studies proposed to alleviate the cold-start problem are also known as hybrid recommender systems that learn representations of users and items by combining user-item interactive and user/item content information. However, previous hybrid methods regularly suffered poor efficiency bottlenecking in online recommendations with large-scale items, because they were designed to project users and items into continuous latent space where the online recommendation is expensive. To this end, we propose a collaborative generated hashing (CGH) framework to improve the efficiency by denoting users and items as binary codes, then fast hashing search techniques can be used to speed up the online recommendation. In addition, the proposed CGH can generate potential users or items for marketing application where the generative network is designed with the principle of Minimum Description Length (MDL), which is used to learn compact and informative binary codes. Extensive experiments on two public datasets show the advantages for recommendations in various settings over competing baselines and analyze its feasibility in marketing application.

Zhiyu Xue, Lixin Duan, Wen Li et al.

While deep learning has been successfully applied to many real-world computer vision tasks, training robust classifiers usually requires a large amount of well-labeled data. However, the annotation is often expensive and time-consuming. Few-shot image classification has thus been proposed to effectively use only a limited number of labeled examples to train models for new classes. Recent works based on transferable metric learning methods have achieved promising classification performance through learning the similarity between the features of samples from the query and support sets. However, rare of them explicitly considers the model interpretability, which can actually be revealed during the training phase. For that, in this work, we propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works as in a neural network as well as to find out specific regions that are related to each other in images coming from the query and support sets. Moreover, we also present a visualization strategy named Region Activation Mapping (RAM) to intuitively explain what our method has learned by visualizing intermediate variables in our network. We also present a new way to generalize the interpretability from the level of tasks to categories, which can also be viewed as a method to find the prototypical parts for supporting the final decision of our RCN. Extensive experiments on four benchmark datasets clearly show the effectiveness of our method over existing baselines.

Chaofan Tao, Qinhong Jiang, Lixin Duan et al.

Multi-agent motion prediction is challenging because it aims to foresee the future trajectories of multiple agents (\textit{e.g.} pedestrians) simultaneously in a complicated scene. Existing work addressed this challenge by either learning social spatial interactions represented by the positions of a group of pedestrians, while ignoring their temporal coherence (\textit{i.e.} dependencies between different long trajectories), or by understanding the complicated scene layout (\textit{e.g.} scene segmentation) to ensure safe navigation. However, unlike previous work that isolated the spatial interaction, temporal coherence, and scene layout, this paper designs a new mechanism, \textit{i.e.}, Dynamic and Static Context-aware Motion Predictor (DSCMP), to integrates these rich information into the long-short-term-memory (LSTM). It has three appealing benefits. (1) DSCMP models the dynamic interactions between agents by learning both their spatial positions and temporal coherence, as well as understanding the contextual scene layout.(2) Different from previous LSTM models that predict motions by propagating hidden features frame by frame, limiting the capacity to learn correlations between long trajectories, we carefully design a differentiable queue mechanism in DSCMP, which is able to explicitly memorize and learn the correlations between long trajectories. (3) DSCMP captures the context of scene by inferring latent variable, which enables multimodal predictions with meaningful semantic scene layout. Extensive experiments show that DSCMP outperforms state-of-the-art methods by large margins, such as 9.05\% and 7.62\% relative improvements on the ETH-UCY and SDD datasets respectively.

Changsheng Li, Chong Liu, Lixin Duan et al.

In this paper, we present a novel deep metric learning method to tackle the multi-label image classification problem. In order to better learn the correlations among images features, as well as labels, we attempt to explore a latent space, where images and labels are embedded via two unique deep neural networks, respectively. To capture the relationships between image features and labels, we aim to learn a \emph{two-way} deep distance metric over the embedding space from two different views, i.e., the distance between one image and its labels is not only smaller than those distances between the image and its labels' nearest neighbors, but also smaller than the distances between the labels and other images corresponding to the labels' nearest neighbors. Moreover, a reconstruction module for recovering correct labels is incorporated into the whole framework as a regularization term, such that the label embedding space is more representative. Our model can be trained in an end-to-end manner. Experimental results on publicly available image datasets corroborate the efficacy of our method compared with the state-of-the-arts.

Minghao Fu, Zhenshan Xie, Wen Li et al.

Cross-domain object detection has recently attracted more and more attention for real-world applications, since it helps build robust detectors adapting well to new environments. In this work, we propose an end-to-end solution based on Faster R-CNN, where ground-truth annotations are available for source images (e.g., cartoon) but not for target ones (e.g., watercolor) during training. Motivated by the observation that the transferabilities of different neural network layers differ from each other, we propose to apply a number of domain alignment strategies to different layers of Faster R-CNN, where the alignment strength is gradually reduced from low to higher layers. Moreover, after obtaining region proposals in our network, we develop a foreground-background aware alignment module to further reduce the domain mismatch by separately aligning features of the foreground and background regions from the source and target domains. Extensive experiments on benchmark datasets demonstrate the effectiveness of our proposed approach.

Fengmao Lv, Jianyang Zhang, Guowu Yang et al.

Zero-Shot Learning (ZSL) learns models for recognizing new classes. One of the main challenges in ZSL is the domain discrepancy caused by the category inconsistency between training and testing data. Domain adaptation is the most intuitive way to address this challenge. However, existing domain adaptation techniques cannot be directly applied into ZSL due to the disjoint label space between source and target domains. This work proposes the Transferrable Semantic-Visual Relation (TSVR) approach towards transductive ZSL. TSVR redefines image recognition as predicting the similarity/dissimilarity labels for semantic-visual fusions consisting of class attributes and visual features. After the above transformation, the source and target domains can have the same label space, which hence enables to quantify domain discrepancy. For the redefined problem, the number of similar semantic-visual pairs is significantly smaller than that of dissimilar ones. To this end, we further propose to use Domain-Specific Batch Normalization to align the domain discrepancy.

Yiming Xu, Lin Chen, Zhongwei Cheng et al.

We study the problem of visual question answering (VQA) in images by exploiting supervised domain adaptation, where there is a large amount of labeled data in the source domain but only limited labeled data in the target domain with the goal to train a good target model. A straightforward solution is to fine-tune a pre-trained source model by using those limited labeled target data, but it usually cannot work well due to the considerable difference between the data distributions of the source and target domains. Moreover, the availability of multiple modalities (i.e., images, questions and answers) in VQA poses further challenges to model the transferability between those different modalities. In this paper, we tackle the above issues by proposing a novel supervised multi-modal domain adaptation method for VQA to learn joint feature embeddings across different domains and modalities. Specifically, we align the data distributions of the source and target domains by considering all modalities together as well as separately for each individual modality. Based on the extensive experiments on the benchmark VQA 2.0 and VizWiz datasets for the realistic open-ended VQA task, we demonstrate that our proposed method outperforms the existing state-of-the-art approaches in this challenging domain adaptation setting for VQA.

Qing Lian, Fengmao Lv, Lixin Duan et al.

We propose a new approach, called self-motivated pyramid curriculum domain adaptation (PyCDA), to facilitate the adaptation of semantic segmentation neural networks from synthetic source domains to real target domains. Our approach draws on an insight connecting two existing works: curriculum domain adaptation and self-training. Inspired by the former, PyCDA constructs a pyramid curriculum which contains various properties about the target domain. Those properties are mainly about the desired label distributions over the target domain images, image regions, and pixels. By enforcing the segmentation neural network to observe those properties, we can improve the network's generalization capability to the target domain. Motivated by the self-training, we infer this pyramid of properties by resorting to the semantic segmentation network itself. Unlike prior work, we do not need to maintain any additional models (e.g., logistic regression or discriminator networks) or to solve minmax problems which are often difficult to optimize. We report state-of-the-art results for the adaptation from both GTAV and SYNTHIA to Cityscapes, two popular settings in unsupervised domain adaptation for semantic segmentation.