Xiaofei He

Yuqi Lin, Minghao Chen, Wenxiao Wang et al.

Weakly supervised semantic segmentation (WSSS) with image-level labels is a challenging task. Mainstream approaches follow a multi-stage framework and suffer from high training costs. In this paper, we explore the potential of Contrastive Language-Image Pre-training models (CLIP) to localize different categories with only image-level labels and without further training. To efficiently generate high-quality segmentation masks from CLIP, we propose a novel WSSS framework called CLIP-ES. Our framework improves all three stages of WSSS with special designs for CLIP: 1) We introduce the softmax function into GradCAM and exploit the zero-shot ability of CLIP to suppress the confusion caused by non-target classes and backgrounds. Meanwhile, to take full advantage of CLIP, we re-explore text inputs under the WSSS setting and customize two text-driven strategies: sharpness-based prompt selection and synonym fusion. 2) To simplify the stage of CAM refinement, we propose a real-time class-aware attention-based affinity (CAA) module based on the inherent multi-head self-attention (MHSA) in CLIP-ViTs. 3) When training the final segmentation model with the masks generated by CLIP, we introduced a confidence-guided loss (CGL) focus on confident regions. Our CLIP-ES achieves SOTA performance on Pascal VOC 2012 and MS COCO 2014 while only taking 10% time of previous methods for the pseudo mask generation. Code is available at https://github.com/linyq2117/CLIP-ES.

Honghui Yang, Tong He, Jiaheng Liu et al.

Despite the tremendous progress of Masked Autoencoders (MAE) in developing vision tasks such as image and video, exploring MAE in large-scale 3D point clouds remains challenging due to the inherent irregularity. In contrast to previous 3D MAE frameworks, which either design a complex decoder to infer masked information from maintained regions or adopt sophisticated masking strategies, we instead propose a much simpler paradigm. The core idea is to apply a \textbf{G}enerative \textbf{D}ecoder for MAE (GD-MAE) to automatically merges the surrounding context to restore the masked geometric knowledge in a hierarchical fusion manner. In doing so, our approach is free from introducing the heuristic design of decoders and enjoys the flexibility of exploring various masking strategies. The corresponding part costs less than \textbf{12\%} latency compared with conventional methods, while achieving better performance. We demonstrate the efficacy of the proposed method on several large-scale benchmarks: Waymo, KITTI, and ONCE. Consistent improvement on downstream detection tasks illustrates strong robustness and generalization capability. Not only our method reveals state-of-the-art results, but remarkably, we achieve comparable accuracy even with \textbf{20\%} of the labeled data on the Waymo dataset. Code will be released at https://github.com/Nightmare-n/GD-MAE.

Honghui Yang, Zili Liu, Xiaopei Wu et al.

Two-stage detectors have gained much popularity in 3D object detection. Most two-stage 3D detectors utilize grid points, voxel grids, or sampled keypoints for RoI feature extraction in the second stage. Such methods, however, are inefficient in handling unevenly distributed and sparse outdoor points. This paper solves this problem in three aspects. 1) Dynamic Point Aggregation. We propose the patch search to quickly search points in a local region for each 3D proposal. The dynamic farthest voxel sampling is then applied to evenly sample the points. Especially, the voxel size varies along the distance to accommodate the uneven distribution of points. 2) RoI-graph Pooling. We build local graphs on the sampled points to better model contextual information and mine point relations through iterative message passing. 3) Visual Features Augmentation. We introduce a simple yet effective fusion strategy to compensate for sparse LiDAR points with limited semantic cues. Based on these modules, we construct our Graph R-CNN as the second stage, which can be applied to existing one-stage detectors to consistently improve the detection performance. Extensive experiments show that Graph R-CNN outperforms the state-of-the-art 3D detection models by a large margin on both the KITTI and Waymo Open Dataset. And we rank first place on the KITTI BEV car detection leaderboard. Code will be available at \url{https://github.com/Nightmare-n/GraphRCNN}.

Boxi Wu, Jindong Gu, Zhifeng Li et al. · deepmind, oxford

Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network (CNN), has received much attention. Recent work showed that ViTs are also vulnerable to adversarial examples like CNNs. To build robust ViTs, an intuitive way is to apply adversarial training since it has been shown as one of the most effective ways to accomplish robust CNNs. However, one major limitation of adversarial training is its heavy computational cost. The self-attention mechanism adopted by ViTs is a computationally intense operation whose expense increases quadratically with the number of input patches, making adversarial training on ViTs even more time-consuming. In this work, we first comprehensively study fast adversarial training on a variety of vision transformers and illustrate the relationship between the efficiency and robustness. Then, to expediate adversarial training on ViTs, we propose an efficient Attention Guided Adversarial Training mechanism. Specifically, relying on the specialty of self-attention, we actively remove certain patch embeddings of each layer with an attention-guided dropping strategy during adversarial training. The slimmed self-attention modules accelerate the adversarial training on ViTs significantly. With only 65\% of the fast adversarial training time, we match the state-of-the-art results on the challenging ImageNet benchmark.

Liang Peng, Senbo Yan, Boxi Wu et al.

Monocular 3D object detection is one of the most challenging tasks in 3D scene understanding. Due to the ill-posed nature of monocular imagery, existing monocular 3D detection methods highly rely on training with the manually annotated 3D box labels on the LiDAR point clouds. This annotation process is very laborious and expensive. To dispense with the reliance on 3D box labels, in this paper we explore the weakly supervised monocular 3D detection. Specifically, we first detect 2D boxes on the image. Then, we adopt the generated 2D boxes to select corresponding RoI LiDAR points as the weak supervision. Eventually, we adopt a network to predict 3D boxes which can tightly align with associated RoI LiDAR points. This network is learned by minimizing our newly-proposed 3D alignment loss between the 3D box estimates and the corresponding RoI LiDAR points. We will illustrate the potential challenges of the above learning problem and resolve these challenges by introducing several effective designs into our method. Codes will be available at https://github.com/SPengLiang/WeakM3D.

Qibo Qiu, Haiming Gao, Wei Hua et al.

Lane detection is one of the fundamental modules in self-driving. In this paper we employ a transformer-only method for lane detection, thus it could benefit from the blooming development of fully vision transformer and achieve the state-of-the-art (SOTA) performance on both CULane and TuSimple benchmarks, by fine-tuning the weight fully pre-trained on large datasets. More importantly, this paper proposes a novel and general framework called PriorLane, which is used to enhance the segmentation performance of the fully vision transformer by introducing the low-cost local prior knowledge. Specifically, PriorLane utilizes an encoder-only transformer to fuse the feature extracted by a pre-trained segmentation model with prior knowledge embeddings. Note that a Knowledge Embedding Alignment (KEA) module is adapted to enhance the fusion performance by aligning the knowledge embedding. Extensive experiments on our Zjlab dataset show that PriorLane outperforms SOTA lane detection methods by a 2.82% mIoU when prior knowledge is employed, and the code will be released at: https://github.com/vincentqqb/PriorLane.

Wenxiao Wang, Wei Chen, Qibo Qiu et al.

While features of different scales are perceptually important to visual inputs, existing vision transformers do not yet take advantage of them explicitly. To this end, we first propose a cross-scale vision transformer, CrossFormer. It introduces a cross-scale embedding layer (CEL) and a long-short distance attention (LSDA). On the one hand, CEL blends each token with multiple patches of different scales, providing the self-attention module itself with cross-scale features. On the other hand, LSDA splits the self-attention module into a short-distance one and a long-distance counterpart, which not only reduces the computational burden but also keeps both small-scale and large-scale features in the tokens. Moreover, through experiments on CrossFormer, we observe another two issues that affect vision transformers' performance, i.e., the enlarging self-attention maps and amplitude explosion. Thus, we further propose a progressive group size (PGS) paradigm and an amplitude cooling layer (ACL) to alleviate the two issues, respectively. The CrossFormer incorporating with PGS and ACL is called CrossFormer++. Extensive experiments show that CrossFormer++ outperforms the other vision transformers on image classification, object detection, instance segmentation, and semantic segmentation tasks. The code will be available at: https://github.com/cheerss/CrossFormer.

Honghui Yang, Sha Zhang, Di Huang et al.

In the context of autonomous driving, the significance of effective feature learning is widely acknowledged. While conventional 3D self-supervised pre-training methods have shown widespread success, most methods follow the ideas originally designed for 2D images. In this paper, we present UniPAD, a novel self-supervised learning paradigm applying 3D volumetric differentiable rendering. UniPAD implicitly encodes 3D space, facilitating the reconstruction of continuous 3D shape structures and the intricate appearance characteristics of their 2D projections. The flexibility of our method enables seamless integration into both 2D and 3D frameworks, enabling a more holistic comprehension of the scenes. We manifest the feasibility and effectiveness of UniPAD by conducting extensive experiments on various downstream 3D tasks. Our method significantly improves lidar-, camera-, and lidar-camera-based baseline by 9.1, 7.7, and 6.9 NDS, respectively. Notably, our pre-training pipeline achieves 73.2 NDS for 3D object detection and 79.4 mIoU for 3D semantic segmentation on the nuScenes validation set, achieving state-of-the-art results in comparison with previous methods. The code will be available at https://github.com/Nightmare-n/UniPAD.

Tu Zheng, Yifei Huang, Yang Liu et al.

Lane is critical in the vision navigation system of the intelligent vehicle. Naturally, lane is a traffic sign with high-level semantics, whereas it owns the specific local pattern which needs detailed low-level features to localize accurately. Using different feature levels is of great importance for accurate lane detection, but it is still under-explored. In this work, we present Cross Layer Refinement Network (CLRNet) aiming at fully utilizing both high-level and low-level features in lane detection. In particular, it first detects lanes with high-level semantic features then performs refinement based on low-level features. In this way, we can exploit more contextual information to detect lanes while leveraging local detailed lane features to improve localization accuracy. We present ROIGather to gather global context, which further enhances the feature representation of lanes. In addition to our novel network design, we introduce Line IoU loss which regresses the lane line as a whole unit to improve the localization accuracy. Experiments demonstrate that the proposed method greatly outperforms the state-of-the-art lane detection approaches.

Liang Xie, Yibo Yang, Deng Cai et al.

Class imbalance distribution widely exists in real-world engineering. However, the mainstream optimization algorithms that seek to minimize error will trap the deep learning model in sub-optimums when facing extreme class imbalance. It seriously harms the classification precision, especially on the minor classes. The essential reason is that the gradients of the classifier weights are imbalanced among the components from different classes. In this paper, we propose Attraction-Repulsion-Balanced Loss (ARB-Loss) to balance the different components of the gradients. We perform experiments on the large-scale classification and segmentation datasets and our ARB-Loss can achieve state-of-the-art performance via only one-stage training instead of 2-stage learning like nowadays SOTA works.

Ke Li, Dong An, Xiaoling Zang et al.

Low-bit activation quantization remains a major bottleneck in efficient large language model (LLM) deployment. The difficulty is not only that activations contain outliers, but that their distributions are often poorly matched to a low-bit uniform quantizer. Existing post-training quantization (PTQ) methods suppress peaks, balance channels, or minimize reconstruction error, yet they rarely specify what activation distribution is actually easy to discretize. As a result, activations may appear numerically smoother while still incurring large quantization error because the quantization range remains wide or most values collapse into a few levels near the mean. We recast activation transformation as quantizer-facing distribution design and analyze quantization error from an information-theoretic perspective. Our analysis shows that quantization-friendly activations should jointly have a smaller numerical range and sufficient dispersion within that range. Guided by this analysis, we propose InfoQuant, a train-free method that employs Peak Suppression Orthogonal Transformation (PSOT) to shape activations into more quantization-friendly distributions. We further introduce adaptive outlier-token selection to improve the robustness of PSOT during optimization. Across multiple LLM families, InfoQuant consistently outperforms prior PTQ and end-to-end training baselines. Under W4A4KV4, it preserves 97% of floating-point accuracy on average and reduces the LLaMA-2 13B performance gap by 42% over the previous state of the art. Code is available at [https://github.com/LLIKKE/InfoQuant](https://github.com/LLIKKE/InfoQuant)

Xing Zhao, Haoran Liang, Peipei Li et al.

Previous methods based on 3DCNN, convLSTM, or optical flow have achieved great success in video salient object detection (VSOD). However, they still suffer from high computational costs or poor quality of the generated saliency maps. To solve these problems, we design a space-time memory (STM)-based network, which extracts useful temporal information of the current frame from adjacent frames as the temporal branch of VSOD. Furthermore, previous methods only considered single-frame prediction without temporal association. As a result, the model may not focus on the temporal information sufficiently. Thus, we initially introduce object motion prediction between inter-frame into VSOD. Our model follows standard encoder--decoder architecture. In the encoding stage, we generate high-level temporal features by using high-level features from the current and its adjacent frames. This approach is more efficient than the optical flow-based methods. In the decoding stage, we propose an effective fusion strategy for spatial and temporal branches. The semantic information of the high-level features is used to fuse the object details in the low-level features, and then the spatiotemporal features are obtained step by step to reconstruct the saliency maps. Moreover, inspired by the boundary supervision commonly used in image salient object detection (ISOD), we design a motion-aware loss for predicting object boundary motion and simultaneously perform multitask learning for VSOD and object motion prediction, which can further facilitate the model to extract spatiotemporal features accurately and maintain the object integrity. Extensive experiments on several datasets demonstrated the effectiveness of our method and can achieve state-of-the-art metrics on some datasets. The proposed model does not require optical flow or other preprocessing, and can reach a speed of nearly 100 FPS during inference.

Yaming Yang, Zhe Wang, Ziyu Guan et al.

Entity alignment (EA) is to identify equivalent entities across different knowledge graphs (KGs), which can help fuse these KGs into a more comprehensive one. Previous EA methods mainly focus on aligning a pair of KGs, and to the best of our knowledge, no existing EA method considers aligning multiple (more than two) KGs. To fill this research gap, in this work, we study a novel problem of aligning multiple KGs and propose an effective framework named MultiEA to solve the problem. First, we embed the entities of all the candidate KGs into a common feature space by a shared KG encoder. Then, we explore three alignment strategies to minimize the distances among pre-aligned entities. In particular, we propose an innovative inference enhancement technique to improve the alignment performance by incorporating high-order similarities. Finally, to verify the effectiveness of MultiEA, we construct two new real-world benchmark datasets and conduct extensive experiments on them. The results show that our MultiEA can effectively and efficiently align multiple KGs in a single pass. We release the source codes of MultiEA at: https://github.com/kepsail/MultiEA.

Jie Zhao, Ziyu Guan, Wei Zhao et al.

Recent works considering professional legal-linguistic style (PLLS) texts have shown promising results on the charge prediction task. However, unprofessional users also show an increasing demand on such a prediction service. There is a clear domain discrepancy between PLLS texts and non-PLLS texts expressed by those laypersons, which degrades the current SOTA models' performance on non-PLLS texts. A key challenge is the scarcity of non-PLLS data for most charge classes. This paper proposes a novel few-shot domain adaptation (FSDA) method named Disentangled Legal Content for Charge Prediction (DLCCP). Compared with existing FSDA works, which solely perform instance-level alignment without considering the negative impact of text style information existing in latent features, DLCCP (1) disentangles the content and style representations for better domain-invariant legal content learning with carefully designed optimization goals for content and style spaces and, (2) employs the constitutive elements knowledge of charges to extract and align element-level and instance-level content representations simultaneously. We contribute the first publicly available non-PLLS dataset named NCCP for developing layperson-friendly charge prediction models. Experiments on NCCP show the superiority of our methods over competitive baselines.

Liang Xie, Yibo Yang, Wenxiao Wang et al.

Compared to 2D images, 3D point clouds are much more sensitive to rotations. We expect the point features describing certain patterns to keep invariant to the rotation transformation. There are many recent SOTA works dedicated to rotation-invariant learning for 3D point clouds. However, current rotation-invariant methods lack generalizability on the point clouds in the open scenes due to the reliance on the global distribution, \ie the global scene and backgrounds. Considering that the output activation is a function of the pattern and its orientation, we need to eliminate the effect of the orientation.In this paper, inspired by the idea that the network weights can be considered a set of points distributed in the same 3D space as the input points, we propose Weight-Feature Alignment (WFA) to construct a local Invariant Reference Frame (IRF) via aligning the features with the principal axes of the network weights. Our WFA algorithm provides a general solution for the point clouds of all scenes. WFA ensures the model achieves the target that the response activity is a necessary and sufficient condition of the pattern matching degree. Practically, we perform experiments on the point clouds of both single objects and open large-range scenes. The results suggest that our method almost bridges the gap between rotation invariance learning and normal methods.

Yang Yang, Tianyi Zhang, Wei Huang et al.

Interactive long video generation requires prompt switching to introduce new subjects or events, while maintaining perceptual fidelity and coherent motion over extended horizons. Recent distilled streaming video diffusion models reuse a rolling KV cache for long-range generation, enabling prompt-switch interaction through re-cache at each switch. However, existing streaming methods still exhibit progressive quality degradation and weakened motion dynamics. We identify two failure modes specific to interactive streaming generation: (i) at each prompt switch, current cache maintenance cannot simultaneously retain KV-based semantic context and recent latent cues, resulting in weak boundary conditioning and reduced perceptual quality; and (ii) during distillation, unbounded time indexing induces a positional distribution shift from the pretrained backbone's bounded RoPE regime, weakening pretrained motion priors and long-horizon motion retention. To address these issues, we propose \textbf{Anchor Forcing}, a cache-centric framework with two designs. First, an anchor-guided re-cache mechanism stores KV states in anchor caches and warm-starts re-cache from these anchors at each prompt switch, reducing post-switch evidence loss and stabilizing perceptual quality. Second, a tri-region RoPE with region-specific reference origins, together with RoPE re-alignment distillation, reconciles unbounded streaming indices with the pretrained RoPE regime to better retain motion priors. Experiments on long videos show that our method improves perceptual quality and motion metrics over prior streaming baselines in interactive settings. Project page: https://github.com/vivoCameraResearch/Anchor-Forcing

Minghao Chen, Zepeng Gao, Shuai Zhao et al.

Unsupervised domain adaptation (UDA) methods facilitate the transfer of models to target domains without labels. However, these methods necessitate a labeled target validation set for hyper-parameter tuning and model selection. In this paper, we aim to find an evaluation metric capable of assessing the quality of a transferred model without access to target validation labels. We begin with the metric based on mutual information of the model prediction. Through empirical analysis, we identify three prevalent issues with this metric: 1) It does not account for the source structure. 2) It can be easily attacked. 3) It fails to detect negative transfer caused by the over-alignment of source and target features. To address the first two issues, we incorporate source accuracy into the metric and employ a new MLP classifier that is held out during training, significantly improving the result. To tackle the final issue, we integrate this enhanced metric with data augmentation, resulting in a novel unsupervised UDA metric called the Augmentation Consistency Metric (ACM). Additionally, we empirically demonstrate the shortcomings of previous experiment settings and conduct large-scale experiments to validate the effectiveness of our proposed metric. Furthermore, we employ our metric to automatically search for the optimal hyper-parameter set, achieving superior performance compared to manually tuned sets across four common benchmarks. Codes will be available soon.

Boxi Wu, Jie Jiang, Haidong Ren et al.

Deep neural network, despite its remarkable capability of discriminating targeted in-distribution samples, shows poor performance on detecting anomalous out-of-distribution data. To address this defect, state-of-the-art solutions choose to train deep networks on an auxiliary dataset of outliers. Various training criteria for these auxiliary outliers are proposed based on heuristic intuitions. However, we find that these intuitively designed outlier training criteria can hurt in-distribution learning and eventually lead to inferior performance. To this end, we identify three causes of the in-distribution incompatibility: contradictory gradient, false likelihood, and distribution shift. Based on our new understandings, we propose a new out-of-distribution detection method by adapting both the top-design of deep models and the loss function. Our method achieves in-distribution compatibility by pursuing less interference with the probabilistic characteristic of in-distribution features. On several benchmarks, our method not only achieves the state-of-the-art out-of-distribution detection performance but also improves the in-distribution accuracy.

Zhiyuan Shi, Qibo Qiu, Feng Xue et al.

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information, principally because they overlook the attention drift phenomenon where token significance evolves dynamically. Although recent dynamic retrieval approaches attempt to address this issue, they typically suffer from coarse-grained caching strategies and incur high I/O overhead due to frequent data transfers. To overcome these limitations, we propose HeteroCache, a training-free dynamic compression framework. Our method is built on two key insights: attention heads exhibit diverse temporal heterogeneity, and there is significant spatial redundancy among heads within the same layer. Guided by these insights, HeteroCache categorizes heads based on stability and redundancy. Consequently, we apply a fine-grained weighting strategy that allocates larger cache budgets to heads with rapidly shifting attention to capture context changes, thereby addressing the inefficiency of coarse-grained strategies. Furthermore, we employ a hierarchical storage mechanism in which a subset of representative heads monitors attention shift, and trigger an asynchronous, on-demand retrieval of contexts from the CPU, effectively hiding I/O latency. Finally, experiments demonstrate that HeteroCache achieves state-of-the-art performance on multiple long-context benchmarks and accelerates decoding by up to $3\times$ compared to the original model in the 224K context. Our code will be open-source.

Qibo Qiu, Wenxiao Wang, Haochao Ying et al.

Point cloud-based place recognition is crucial for mobile robots and autonomous vehicles, especially when the global positioning sensor is not accessible. LiDAR points are scattered on the surface of objects and buildings, which have strong shape priors along different axes. To enhance message passing along particular axes, Stacked Asymmetric Convolution Block (SACB) is designed, which is one of the main contributions in this paper. Comprehensive experiments demonstrate that asymmetric convolution and its corresponding strategies employed by SACB can contribute to the more effective representation of point cloud feature. On this basis, Selective Feature Fusion Block (SFFB), which is formed by stacking point- and channel-wise gating layers in a predefined sequence, is proposed to selectively boost salient local features in certain key regions, as well as to align the features before fusion phase. SACBs and SFFBs are combined to construct a robust and accurate architecture for point cloud-based place recognition, which is termed SelFLoc. Comparative experimental results show that SelFLoc achieves the state-of-the-art (SOTA) performance on the Oxford and other three in-house benchmarks with an improvement of 1.6 absolute percentages on mean average recall@1.

Honghui Yang, Di Huang, Wei Yin et al.

Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse virtual environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates-even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency. The code and model weights are open-sourced.

Hengjia Li, Yang Liu, Linxuan Xia et al.

Can a pre-trained generator be adapted to the hybrid of multiple target domains and generate images with integrated attributes of them? In this work, we introduce a new task -- Few-shot Hybrid Domain Adaptation (HDA). Given a source generator and several target domains, HDA aims to acquire an adapted generator that preserves the integrated attributes of all target domains, without overriding the source domain's characteristics. Compared with Domain Adaptation (DA), HDA offers greater flexibility and versatility to adapt generators to more composite and expansive domains. Simultaneously, HDA also presents more challenges than DA as we have access only to images from individual target domains and lack authentic images from the hybrid domain. To address this issue, we introduce a discriminator-free framework that directly encodes different domains' images into well-separable subspaces. To achieve HDA, we propose a novel directional subspace loss comprised of a distance loss and a direction loss. Concretely, the distance loss blends the attributes of all target domains by reducing the distances from generated images to all target subspaces. The direction loss preserves the characteristics from the source domain by guiding the adaptation along the perpendicular to subspaces. Experiments show that our method can obtain numerous domain-specific attributes in a single adapted generator, which surpasses the baseline methods in semantic similarity, image fidelity, and cross-domain consistency.

Yanting Yang, Minghao Chen, Qibo Qiu et al.

For a general-purpose robot to operate in reality, executing a broad range of instructions across various environments is imperative. Central to the reinforcement learning and planning for such robotic agents is a generalizable reward function. Recent advances in vision-language models, such as CLIP, have shown remarkable performance in the domain of deep learning, paving the way for open-domain visual recognition. However, collecting data on robots executing various language instructions across multiple environments remains a challenge. This paper aims to transfer video-language models with robust generalization into a generalizable language-conditioned reward function, only utilizing robot video data from a minimal amount of tasks in a singular environment. Unlike common robotic datasets used for training reward functions, human video-language datasets rarely contain trivial failure videos. To enhance the model's ability to distinguish between successful and failed robot executions, we cluster failure video features to enable the model to identify patterns within. For each cluster, we integrate a newly trained failure prompt into the text encoder to represent the corresponding failure mode. Our language-conditioned reward function shows outstanding generalization to new environments and new instructions for robot planning and reinforcement learning.

Chenshu Hou, Liang Peng, Xiaopei Wu et al.

3D visual grounding aims to identify objects in 3D point cloud scenes that match specific natural language descriptions. This requires the model to not only focus on the target object itself but also to consider the surrounding environment to determine whether the descriptions are met. Most previous works attempt to accomplish both tasks within the same module, which can easily lead to a distraction of attention. To this end, we propose PD-APE, a dual-branch decoding framework that separately decodes target object attributes and surrounding layouts. Specifically, in the target object branch, the decoder processes text tokens that describe features of the target object (e.g., category and color), guiding the queries to pay attention to the target object itself. In the surrounding branch, the queries align with other text tokens that carry surrounding environment information, making the attention maps accurately capture the layout described in the text. Benefiting from the proposed dual-branch design, the queries are allowed to focus on points relevant to each branch's specific objective. Moreover, we design an adaptive position encoding method for each branch respectively. In the target object branch, the position encoding relies on the relative positions between seed points and predicted 3D boxes. In the surrounding branch, the attention map is additionally guided by the confidence between visual and text features, enabling the queries to focus on points that have valuable layout information. Extensive experiments demonstrate that we surpass the state-of-the-art on two widely adopted 3D visual grounding datasets, ScanRefer and Nr3D.

Yuqi Lin, Hengjia Li, Wenqi Shao et al.

In this paper, we explore a principal way to enhance the quality of widely pre-existing coarse masks, enabling them to serve as reliable training data for segmentation models to reduce the annotation cost. In contrast to prior refinement techniques that are tailored to specific models or tasks in a close-world manner, we propose SAMRefiner, a universal and efficient approach by adapting SAM to the mask refinement task. The core technique of our model is the noise-tolerant prompting scheme. Specifically, we introduce a multi-prompt excavation strategy to mine diverse input prompts for SAM (i.e., distance-guided points, context-aware elastic bounding boxes, and Gaussian-style masks) from initial coarse masks. These prompts can collaborate with each other to mitigate the effect of defects in coarse masks. In particular, considering the difficulty of SAM to handle the multi-object case in semantic segmentation, we introduce a split-then-merge (STM) pipeline. Additionally, we extend our method to SAMRefiner++ by introducing an additional IoU adaption step to further boost the performance of the generic SAMRefiner on the target dataset. This step is self-boosted and requires no additional annotation. The proposed framework is versatile and can flexibly cooperate with existing segmentation methods. We evaluate our mask framework on a wide range of benchmarks under different settings, demonstrating better accuracy and efficiency. SAMRefiner holds significant potential to expedite the evolution of refinement tools. Our code is available at https://github.com/linyq2117/SAMRefiner.

Yibo Zhao, Hengjia Li, Xiaofei He et al.

Recent diffusion-based video generation models can synthesize visually plausible videos, yet they often struggle to satisfy physical constraints. A key reason is that most existing approaches remain single-stage: they entangle high-level physical understanding with low-level visual synthesis, making it hard to generate content that require explicit physical reasoning. To address this limitation, we propose a training-free three-stage pipeline,\textit{PhyRPR}:\textit{Phy\uline{R}eason}--\textit{Phy\uline{P}lan}--\textit{Phy\uline{R}efine}, which decouples physical understanding from visual synthesis. Specifically, \textit{PhyReason} uses a large multimodal model for physical state reasoning and an image generator for keyframe synthesis; \textit{PhyPlan} deterministically synthesizes a controllable coarse motion scaffold; and \textit{PhyRefine} injects this scaffold into diffusion sampling via a latent fusion strategy to refine appearance while preserving the planned dynamics. This staged design enables explicit physical control during generation. Extensive experiments under physics constraints show that our method consistently improves physical plausibility and motion controllability.

Yuxin Xiao, Chaoqun Wan, Yonggang Zhang et al.

As the development and application of Large Language Models (LLMs) continue to advance rapidly, enhancing their trustworthiness and aligning them with human preferences has become a critical area of research. Traditional methods rely heavily on extensive data for Reinforcement Learning from Human Feedback (RLHF), but representation engineering offers a new, training-free approach. This technique leverages semantic features to control the representation of LLM's intermediate hidden states, enabling the model to meet specific requirements such as increased honesty or heightened safety awareness. However, a significant challenge arises when attempting to fulfill multiple requirements simultaneously. It proves difficult to encode various semantic contents, like honesty and safety, into a singular semantic feature, restricting its practicality. In this work, we address this issue through ``Sparse Activation Control''. By delving into the intrinsic mechanisms of LLMs, we manage to identify and pinpoint components that are closely related to specific tasks within the model, i.e., attention heads. These heads display sparse characteristics that allow for near-independent control over different tasks. Our experiments, conducted on the open-source Llama series models, have yielded encouraging results. The models were able to align with human preferences on issues of safety, factuality, and bias concurrently.

Qibo Qiu, Honghui Yang, Wenxiao Wang et al.

Masked point modeling has become a promising scheme of self-supervised pre-training for point clouds. Existing methods reconstruct either the original points or related features as the objective of pre-training. However, considering the diversity of downstream tasks, it is necessary for the model to have both low- and high-level representation modeling capabilities to capture geometric details and semantic contexts during pre-training. To this end, M$^3$CS is proposed to enable the model with the above abilities. Specifically, with masked point cloud as input, M$^3$CS introduces two decoders to predict masked representations and the original points simultaneously. While an extra decoder doubles parameters for the decoding process and may lead to overfitting, we propose siamese decoders to keep the amount of learnable parameters unchanged. Further, we propose an online codebook projecting continuous tokens into discrete ones before reconstructing masked points. In such way, we can enforce the decoder to take effect through the combinations of tokens rather than remembering each token. Comprehensive experiments show that M$^3$CS achieves superior performance at both classification and segmentation tasks, outperforming existing methods.

Liang Peng, Boxi Wu, Haoran Cheng et al.

Previous text-to-image diffusion models typically employ supervised fine-tuning (SFT) to enhance pre-trained base models. However, this approach primarily minimizes the loss of mean squared error (MSE) at the pixel level, neglecting the need for global optimization at the image level, which is crucial for achieving high perceptual quality and structural coherence. In this paper, we introduce Self-sUpervised Direct preference Optimization (SUDO), a novel paradigm that optimizes both fine-grained details at the pixel level and global image quality. By integrating direct preference optimization into the model, SUDO generates preference image pairs in a self-supervised manner, enabling the model to prioritize global-level learning while complementing the pixel-level MSE loss. As an effective alternative to supervised fine-tuning, SUDO can be seamlessly applied to any text-to-image diffusion model. Importantly, it eliminates the need for costly data collection and annotation efforts typically associated with traditional direct preference optimization methods. Through extensive experiments on widely-used models, including Stable Diffusion 1.5 and XL, we demonstrate that SUDO significantly enhances both global and local image quality. The codes are provided at \href{https://github.com/SPengLiang/SUDO}{this link}.

Honghui Yang, Wenxiao Wang, Minghao Chen et al.

Recent Transformer-based 3D object detectors learn point cloud features either from point- or voxel-based representations. However, the former requires time-consuming sampling while the latter introduces quantization errors. In this paper, we present a novel Point-Voxel Transformer for single-stage 3D detection (PVT-SSD) that takes advantage of these two representations. Specifically, we first use voxel-based sparse convolutions for efficient feature encoding. Then, we propose a Point-Voxel Transformer (PVT) module that obtains long-range contexts in a cheap manner from voxels while attaining accurate positions from points. The key to associating the two different representations is our introduced input-dependent Query Initialization module, which could efficiently generate reference points and content queries. Then, PVT adaptively fuses long-range contextual and local geometric information around reference points into content queries. Further, to quickly find the neighboring points of reference points, we design the Virtual Range Image module, which generalizes the native range image to multi-sensor and multi-frame. The experiments on several autonomous driving benchmarks verify the effectiveness and efficiency of the proposed method. Code will be available at https://github.com/Nightmare-n/PVT-SSD.

Jiong Wang, Zhou Zhao, Weike Jin et al.

For face presentation attack detection (PAD), most of the spoofing cues are subtle, local image patterns (e.g., local image distortion, 3D mask edge and cut photo edges). The representations of existing PAD works with simple global pooling method, however, lose the local feature discriminability. In this paper, the VLAD aggregation method is adopted to quantize local features with visual vocabulary locally partitioning the feature space, and hence preserve the local discriminability. We further propose the vocabulary separation and adaptation method to modify VLAD for cross-domain PADtask. The proposed vocabulary separation method divides vocabulary into domain-shared and domain-specific visual words to cope with the diversity of live and attack faces under the cross-domain scenario. The proposed vocabulary adaptation method imitates the maximization step of the k-means algorithm in the end-to-end training, which guarantees the visual words be close to the center of assigned local features and thus brings robust similarity measurement. We give illustrations and extensive experiments to demonstrate the effectiveness of VLAD with the proposed vocabulary separation and adaptation method on standard cross-domain PAD benchmarks. The codes are available at https://github.com/Liubinggunzu/VLAD-VSA.

Wenxiao Wang, Lu Yao, Long Chen et al.

Transformers have made great progress in dealing with computer vision tasks. However, existing vision transformers do not yet possess the ability of building the interactions among features of different scales, which is perceptually important to visual inputs. The reasons are two-fold: (1) Input embeddings of each layer are equal-scale, so no cross-scale feature can be extracted; (2) to lower the computational cost, some vision transformers merge adjacent embeddings inside the self-attention module, thus sacrificing small-scale (fine-grained) features of the embeddings and also disabling the cross-scale interactions. To this end, we propose Cross-scale Embedding Layer (CEL) and Long Short Distance Attention (LSDA). On the one hand, CEL blends each embedding with multiple patches of different scales, providing the self-attention module itself with cross-scale features. On the other hand, LSDA splits the self-attention module into a short-distance one and a long-distance counterpart, which not only reduces the computational burden but also keeps both small-scale and large-scale features in the embeddings. Through the above two designs, we achieve cross-scale attention. Besides, we put forward a dynamic position bias for vision transformers to make the popular relative position bias apply to variable-sized images. Hinging on the cross-scale attention module, we construct a versatile vision architecture, dubbed CrossFormer, which accommodates variable-sized inputs. Extensive experiments show that CrossFormer outperforms the other vision transformers on image classification, object detection, instance segmentation, and semantic segmentation tasks. The code has been released: https://github.com/cheerss/CrossFormer.

Jia Guo, Minghao Chen, Yao Hu et al.

Knowledge distillation aims at obtaining a compact and effective model by learning the mapping function from a much larger one. Due to the limited capacity of the student, the student would underfit the teacher. Therefore, student performance would unexpectedly drop when distilling from an oversized teacher, termed the capacity gap problem. We investigate this problem by study the gap of confidence between teacher and student. We find that the magnitude of confidence is not necessary for knowledge distillation and could harm the student performance if the student are forced to learn confidence. We propose Spherical Knowledge Distillation to eliminate this gap explicitly, which eases the underfitting problem. We find this novel knowledge representation can improve compact models with much larger teachers and is robust to temperature. We conducted experiments on both CIFAR100 and ImageNet, and achieve significant improvement. Specifically, we train ResNet18 to 73.0 accuracy, which is a substantial improvement over previous SOTA and is on par with resnet34 almost twice the student size. The implementation has been shared at https://github.com/forjiuzhou/Spherical-Knowledge-Distillation.

Wenxiao Wang, Cong Fu, Jishun Guo et al.

Neural network compression empowers the effective yet unwieldy deep convolutional neural networks (CNN) to be deployed in resource-constrained scenarios. Most state-of-the-art approaches prune the model in filter-level according to the "importance" of filters. Despite their success, we notice they suffer from at least two of the following problems: 1) The redundancy among filters is not considered because the importance is evaluated independently. 2) Cross-layer filter comparison is unachievable since the importance is defined locally within each layer. Consequently, we must manually specify layer-wise pruning ratios. 3) They are prone to generate sub-optimal solutions because they neglect the inequality between reducing parameters and reducing computational cost. Reducing the same number of parameters in different positions in the network may reduce different computational cost. To address the above problems, we develop a novel algorithm named as COP (correlation-based pruning), which can detect the redundant filters efficiently. We enable the cross-layer filter comparison through global normalization. We add parameter-quantity and computational-cost regularization terms to the importance, which enables the users to customize the compression according to their preference (smaller or faster). Extensive experiments have shown COP outperforms the others significantly. The code is released at https://github.com/ZJULearning/COP.

Wenxiao Wang, Wei Chen, Yicong Luo et al.

Transformer based large language models have achieved tremendous success. However, the significant memory and computational costs incurred during the inference process make it challenging to deploy large models on resource-constrained devices. In this paper, we investigate compression and efficient inference methods for large language models from an algorithmic perspective. Regarding taxonomy, similar to smaller models, compression and acceleration algorithms for large language models can still be categorized into quantization, pruning, distillation, compact architecture design, dynamic networks. However, Large language models have two prominent characteristics compared to smaller models: (1) Most of compression algorithms require finetuning or even retraining the model after compression. The most notable aspect of large models is the very high cost associated with model finetuning or training. Therefore, many algorithms for large models, such as quantization and pruning, start to explore tuning-free algorithms. (2) Large models emphasize versatility and generalization rather than performance on a single task. Hence, many algorithms, such as knowledge distillation, focus on how to preserving their versatility and generalization after compression. Since these two characteristics were not very pronounced in early large models, we further distinguish large language models into medium models and ``real'' large models. Additionally, we also provide an introduction to some mature frameworks for efficient inference of large models, which can support basic compression or acceleration algorithms, greatly facilitating model deployment for users.

Wenxiao Wang, Lihui Gu, Liye Zhang et al.

The rapid advancement of large language models (LLMs) has opened new possibilities for automating the proposal of innovative scientific ideas. This process involves two key phases: literature retrieval and idea generation. However, existing approaches often fall short due to their reliance on keyword-based search tools during the retrieval phase, which neglects crucial semantic information and frequently results in incomplete retrieval outcomes. Similarly, in the idea generation phase, current methodologies tend to depend solely on the internal knowledge of LLMs or metadata from retrieved papers, thereby overlooking significant valuable insights contained within the full texts. To address these limitations, we introduce SciPIP, an innovative framework designed to enhance the LLM-based proposal of scientific ideas through improvements in both literature retrieval and idea generation. Our approach begins with the construction of a comprehensive literature database that supports advanced retrieval based not only on keywords but also on semantics and citation relationships. This is complemented by the introduction of a multi-granularity retrieval algorithm aimed at ensuring more thorough and exhaustive retrieval results. For the idea generation phase, we propose a dual-path framework that effectively integrates both the content of retrieved papers and the extensive internal knowledge of LLMs. This integration significantly boosts the novelty, feasibility, and practical value of proposed ideas. Our experiments, conducted across various domains such as natural language processing and computer vision, demonstrate SciPIP's capability to generate a multitude of innovative and useful ideas. These findings underscore SciPIP's potential as a valuable tool for researchers seeking to advance their fields with groundbreaking concepts.

Yilin Zhang, Cai Xu, Han Jiang et al.

Multi-view learning methods often focus on improving decision accuracy while neglecting the decision uncertainty, which significantly restricts their applications in safety-critical scenarios. To address this, trusted multi-view learning methods estimate prediction uncertainties by learning class distributions from each instance. However, these methods heavily rely on high quality ground-truth labels. This motivates us to delve into a new problem: how to develop a reliable multi-view learning model under the guidance of noisy labels? We propose the Trusted Multi view Noise Refining (TMNR) method to address this challenge by modeling label noise arising from low-quality data features and easily-confused classes. TMNR employs evidential deep neural networks to construct view-specific opinions that capture both beliefs and uncertainty. These opinions are then transformed through noise correlation matrices to align with the noisy supervision, where matrix elements are constrained by sample uncertainty to reflect label reliability. Furthermore, considering the challenge of jointly optimizing the evidence network and noise correlation matrices under noisy supervision, we further propose Trusted Multi-view Noise Re-Refining (TMNR^2 ), which disentangles this complex co-training problem by establishing different training objectives for distinct modules. TMNR^2 identifies potentially mislabeled samples through evidence-label consistency and generates pseudo-labels from neighboring information. By assigning clean samples to optimize evidential networks and noisy samples to guide noise correlation matrices, respectively, TMNR^2 reduces mapping interference and achieves stabilizes training. Experimental results demonstrate that TMNR^2 significantly outperforms baseline methods, with average accuracy improvements of 7% on datasets with 50% label noise.

Yibo Zhao, Liang Peng, Yang Yang et al.

Diffusion models have exhibited impressive prowess in the text-to-image task. Recent methods add image-level structure controls, e.g., edge and depth maps, to manipulate the generation process together with text prompts to obtain desired images. This controlling process is globally operated on the entire image, which limits the flexibility of control regions. In this paper, we explore a novel and practical task setting: local control. It focuses on controlling specific local region according to user-defined image conditions, while the remaining regions are only conditioned by the original text prompt. However, it is non-trivial to achieve local conditional controlling. The naive manner of directly adding local conditions may lead to the local control dominance problem, which forces the model to focus on the controlled region and neglect object generation in other regions. To mitigate this problem, we propose Regional Discriminate Loss to update the noised latents, aiming at enhanced object generation in non-control regions. Furthermore, the proposed Focused Token Response suppresses weaker attention scores which lack the strongest response to enhance object distinction and reduce duplication. Lastly, we adopt Feature Mask Constraint to reduce quality degradation in images caused by information differences across the local control region. All proposed strategies are operated at the inference stage. Extensive experiments demonstrate that our method can synthesize high-quality images aligned with the text prompt under local control conditions.

Sinan Fan, Liang Xie, Chen Shen et al.

Prompt-tuning (PT) for large language models (LLMs) can facilitate the performance on various conventional NLP tasks with significantly fewer trainable parameters. However, our investigation reveals that PT provides limited improvement and may even degrade the primitive performance of LLMs on complex reasoning tasks. Such a phenomenon suggests that soft prompts can positively impact certain instances while negatively affecting others, particularly during the later phases of reasoning. To address these challenges, We first identify an information accumulation within the soft prompts. Through detailed analysis, we demonstrate that this phenomenon is often accompanied by erroneous information flow patterns in the deeper layers of the model, which ultimately lead to incorrect reasoning outcomes. we propose a novel method called Dynamic Prompt Corruption (DPC) to take better advantage of soft prompts in complex reasoning tasks, which dynamically adjusts the influence of soft prompts based on their impact on the reasoning process. Specifically, DPC consists of two stages: Dynamic Trigger and Dynamic Corruption. First, Dynamic Trigger measures the impact of soft prompts, identifying whether beneficial or detrimental. Then, Dynamic Corruption mitigates the negative effects of soft prompts by selectively masking key tokens that interfere with the reasoning process. We validate the proposed approach through extensive experiments on various LLMs and reasoning tasks, including GSM8K, MATH, and AQuA. Experimental results demonstrate that DPC can consistently enhance the performance of PT, achieving 4%-8% accuracy gains compared to vanilla prompt tuning, highlighting the effectiveness of our approach and its potential to enhance complex reasoning in LLMs.

Haoran Cheng, Qide Dong, Liang Peng et al.

Direct Preference Optimization (DPO), which aligns models with human preferences through win/lose data pairs, has achieved remarkable success in language and image generation. However, applying DPO to video diffusion models faces critical challenges: (1) Data inefficiency. Generating thousands of videos per DPO iteration incurs prohibitive costs; (2) Evaluation uncertainty. Human annotations suffer from subjective bias, and automated discriminators fail to detect subtle temporal artifacts like flickering or motion incoherence. To address these, we propose a discriminator-free video DPO framework that: (1) Uses original real videos as win cases and their edited versions (e.g., reversed, shuffled, or noise-corrupted clips) as lose cases; (2) Trains video diffusion models to distinguish and avoid artifacts introduced by editing. This approach eliminates the need for costly synthetic video comparisons, provides unambiguous quality signals, and enables unlimited training data expansion through simple editing operations. We theoretically prove the framework's effectiveness even when real videos and model-generated videos follow different distributions. Experiments on CogVideoX demonstrate the efficiency of the proposed method.

Yaming Yang, Zhe Wang, Ziyu Guan et al.

Entity Alignment (EA) is to link potential equivalent entities across different knowledge graphs (KGs). Most existing EA methods are supervised as they require the supervision of seed alignments, i.e., manually specified aligned entity pairs. Very recently, several EA studies have made some attempts to get rid of seed alignments. Despite achieving preliminary progress, they still suffer two limitations: (1) The entity embeddings produced by their GNN-like encoders lack personalization since some of the aggregation subpaths are shared between different entities. (2) They cannot fully alleviate the distribution distortion issue between candidate KGs due to the absence of the supervised signal. In this work, we propose a novel unsupervised entity alignment approach called UNEA to address the above two issues. First, we parametrically sample a tree neighborhood rooted at each entity, and accordingly develop a tree attention aggregation mechanism to extract a personalized embedding for each entity. Second, we introduce an auxiliary task of maximizing the mutual information between the input and the output of the KG encoder, to regularize the model and prevent the distribution distortion. Extensive experiments show that our UNEA achieves a new state-of-the-art for the unsupervised EA task, and can even outperform many existing supervised EA baselines.

Cai Xu, Jinlong Liu, Yilin Zhang et al.

Incomplete Multi-view Clustering (IMC) has emerged as a significant challenge in multi-view learning. A predominant line for IMC is data imputation; however, indiscriminate imputation can result in unreliable content. Recently, researchers have proposed selective imputation methods that use a post-imputation assessment strategy: (1) impute all or some missing values, and (2) evaluate their quality through clustering tasks. We observe that this strategy incurs substantial computational complexity and is heavily dependent on the performance of the clustering model. To address these challenges, we first introduce the concept of pre-imputation assessment. We propose an Implicit Informativeness-based Selective Imputation (SI$^3$) method for incomplete multi-view clustering, which explicitly addresses the trade-off between imputation utility and imputation risk. SI$^3$ evaluates the imputation-relevant informativeness of each missing position in a training-free manner, and selectively imputes data only when sufficient informative support is available. Under a multi-view generative assumption, SI$^3$ further integrates selective imputation into a variational inference framework, enabling uncertainty-aware imputation at the latent distribution level and robust multi-view fusion. Compared with existing selective imputation strategies, SI$^3$ is lightweight, data-driven, and model-agnostic, and can be seamlessly incorporated into existing incomplete multi-view clustering frameworks as a plug-in strategy. Extensive experiments on multiple benchmark datasets demonstrate that SI$^3$ consistently outperforms both imputation-based and imputation-free methods, particularly under challenging unbalanced missing scenarios.

Yang Yang, Siming Zheng, Qirui Yang et al.

Diffusion models have recently emerged as powerful tools for camera simulation, enabling both geometric transformations and realistic optical effects. Among these, image-based bokeh rendering has shown promising results, but diffusion for video bokeh remains unexplored. Existing image-based methods are plagued by temporal flickering and inconsistent blur transitions, while current video editing methods lack explicit control over the focus plane and bokeh intensity. These issues limit their applicability for controllable video bokeh. In this work, we propose a one-step diffusion framework for generating temporally coherent, depth-aware video bokeh rendering. The framework employs a multi-plane image (MPI) representation adapted to the focal plane to condition the video diffusion model, thereby enabling it to exploit strong 3D priors from pretrained backbones. To further enhance temporal stability, depth robustness, and detail preservation, we introduce a progressive training strategy. Experiments on synthetic and real-world benchmarks demonstrate superior temporal coherence, spatial accuracy, and controllability, outperforming prior baselines. This work represents the first dedicated diffusion framework for video bokeh generation, establishing a new baseline for temporally coherent and controllable depth-of-field effects.

Haoran Cheng, Liang Peng, Linxuan Xia et al.

Significant advancements in video diffusion models have brought substantial progress to the field of text-to-video (T2V) synthesis. However, existing T2V synthesis model struggle to accurately generate complex motion dynamics, leading to a reduction in video realism. One possible solution is to collect massive data and train the model on it, but this would be extremely expensive. To alleviate this problem, in this paper, we reformulate the typical T2V generation process as a search-based generation pipeline. Instead of scaling up the model training, we employ existing videos as the motion prior database. Specifically, we divide T2V generation process into two steps: (i) For a given prompt input, we search existing text-video datasets to find videos with text labels that closely match the prompt motions. We propose a tailored search algorithm that emphasizes object motion features. (ii) Retrieved videos are processed and distilled into motion priors to fine-tune a pre-trained base T2V model, followed by generating desired videos using input prompt. By utilizing the priors gleaned from the searched videos, we enhance the realism of the generated videos' motion. All operations can be finished on a single NVIDIA RTX 4090 GPU. We validate our method against state-of-the-art T2V models across diverse prompt inputs. The code will be public.

Aoxiong Yin, Zhou Zhao, Jinglin Liu et al.

Sign language translation as a kind of technology with profound social significance has attracted growing researchers' interest in recent years. However, the existing sign language translation methods need to read all the videos before starting the translation, which leads to a high inference latency and also limits their application in real-life scenarios. To solve this problem, we propose SimulSLT, the first end-to-end simultaneous sign language translation model, which can translate sign language videos into target text concurrently. SimulSLT is composed of a text decoder, a boundary predictor, and a masked encoder. We 1) use the wait-k strategy for simultaneous translation. 2) design a novel boundary predictor based on the integrate-and-fire module to output the gloss boundary, which is used to model the correspondence between the sign language video and the gloss. 3) propose an innovative re-encode method to help the model obtain more abundant contextual information, which allows the existing video features to interact fully. The experimental results conducted on the RWTH-PHOENIX-Weather 2014T dataset show that SimulSLT achieves BLEU scores that exceed the latest end-to-end non-simultaneous sign language translation model while maintaining low latency, which proves the effectiveness of our method.

Jiahao Xun, Shengyu Zhang, Zhou Zhao et al.

There is a soaring interest in the news recommendation research scenario due to the information overload. To accurately capture users' interests, we propose to model multi-modal features, in addition to the news titles that are widely used in existing works, for news recommendation. Besides, existing research pays little attention to the click decision-making process in designing multi-modal modeling modules. In this work, inspired by the fact that users make their click decisions mostly based on the visual impression they perceive when browsing news, we propose to capture such visual impression information with visual-semantic modeling for news recommendation. Specifically, we devise the local impression modeling module to simultaneously attend to decomposed details in the impression when understanding the semantic meaning of news title, which could explicitly get close to the process of users reading news. In addition, we inspect the impression from a global view and take structural information, such as the arrangement of different fields and spatial position of different words on the impression, into the modeling of multiple modalities. To accommodate the research of visual impression-aware news recommendation, we extend the text-dominated news recommendation dataset MIND by adding snapshot impression images and will release it to nourish the research field. Extensive comparisons with the state-of-the-art news recommenders along with the in-depth analyses demonstrate the effectiveness of the proposed method and the promising capability of modeling visual impressions for the content-based recommenders.

Zhijie Lin, Zhou Zhao, Haoyuan Li et al.

Lip reading, aiming to recognize spoken sentences according to the given video of lip movements without relying on the audio stream, has attracted great interest due to its application in many scenarios. Although prior works that explore lip reading have obtained salient achievements, they are all trained in a non-simultaneous manner where the predictions are generated requiring access to the full video. To breakthrough this constraint, we study the task of simultaneous lip reading and devise SimulLR, a simultaneous lip Reading transducer with attention-guided adaptive memory from three aspects: (1) To address the challenge of monotonic alignments while considering the syntactic structure of the generated sentences under simultaneous setting, we build a transducer-based model and design several effective training strategies including CTC pre-training, model warm-up and curriculum learning to promote the training of the lip reading transducer. (2) To learn better spatio-temporal representations for simultaneous encoder, we construct a truncated 3D convolution and time-restricted self-attention layer to perform the frame-to-frame interaction within a video segment containing fixed number of frames. (3) The history information is always limited due to the storage in real-time scenarios, especially for massive video data. Therefore, we devise a novel attention-guided adaptive memory to organize semantic information of history segments and enhance the visual representations with acceptable computation-aware latency. The experiments show that the SimulLR achieves the translation speedup 9.10$\times$ compared with the state-of-the-art non-simultaneous methods, and also obtains competitive results, which indicates the effectiveness of our proposed methods.

Yang Liu, Weifeng Zhang, Chao Xiang et al.

Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to accommodate new tasks not seen during training, given only a few examples. To handle the limited-data problem in few-shot regimes, recent methods tend to collectively use a set of local features to densely represent an image instead of using a mixed global feature. They generally explore a unidirectional query-to-support paradigm in FSL, e.g., find the nearest/optimal support feature for each query feature and aggregate these local matches for a joint classification. In this paper, we propose a new method Mutual Centralized Learning (MCL) to fully affiliate the two disjoint sets of dense features in a bidirectional paradigm. We associate each local feature with a particle that can bidirectionally random walk in a discrete feature space by the affiliations. To estimate the class probability, we propose the features' accessibility that measures the expected number of visits to the support features of that class in a Markov process. We relate our method to learning a centrality on an affiliation network and demonstrate its capability to be plugged in existing methods by highlighting centralized local features. Experiments show that our method achieves the state-of-the-art on both miniImageNet and tieredImageNet.

Hao Fang, Daoxin Zhang, Yi Zhang et al.

Instance segmentation can detect where the objects are in an image, but hard to understand the relationship between them. We pay attention to a typical relationship, relative saliency. A closely related task, salient object detection, predicts a binary map highlighting a visually salient region while hard to distinguish multiple objects. Directly combining two tasks by post-processing also leads to poor performance. There is a lack of research on relative saliency at present, limiting the practical applications such as content-aware image cropping, video summary, and image labeling. In this paper, we study the Salient Object Ranking (SOR) task, which manages to assign a ranking order of each detected object according to its visual saliency. We propose the first end-to-end framework of the SOR task and solve it in a multi-task learning fashion. The framework handles instance segmentation and salient object ranking simultaneously. In this framework, the SOR branch is independent and flexible to cooperate with different detection methods, so that easy to use as a plugin. We also introduce a Position-Preserved Attention (PPA) module tailored for the SOR branch. It consists of the position embedding stage and feature interaction stage. Considering the importance of position in saliency comparison, we preserve absolute coordinates of objects in ROI pooling operation and then fuse positional information with semantic features in the first stage. In the feature interaction stage, we apply the attention mechanism to obtain proposals' contextualized representations to predict their relative ranking orders. Extensive experiments have been conducted on the ASR dataset. Without bells and whistles, our proposed method outperforms the former state-of-the-art method significantly. The code will be released publicly available.

Boxi Wu, Heng Pan, Li Shen et al.

It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we find that the adversarial attacks can also be vulnerable to small perturbations. Namely, on adversarially-trained models, perturbing adversarial examples with a small random noise may invalidate their misled predictions. After carefully examining state-of-the-art attacks of various kinds, we find that all these attacks have this deficiency to different extents. Enlightened by this finding, we propose to counter attacks by crafting more effective defensive perturbations. Our defensive perturbations leverage the advantage that adversarial training endows the ground-truth class with smaller local Lipschitzness. By simultaneously attacking all the classes, the misled predictions with larger Lipschitzness can be flipped into correct ones. We verify our defensive perturbation with both empirical experiments and theoretical analyses on a linear model. On CIFAR10, it boosts the state-of-the-art model from 66.16% to 72.66% against the four attacks of AutoAttack, including 71.76% to 83.30% against the Square attack. On ImageNet, the top-1 robust accuracy of FastAT is improved from 33.18% to 38.54% under the 100-step PGD attack.