Yaowei Wang

Yi Zhang, Jitao Sang, Junyang Wang et al.

Machine learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, such as hiring, banking, and criminal justice. Existing work tackles this issue by minimizing the employed information about social attributes in models for debiasing. However, the high correlation between target task and these social attributes makes learning on the target task incompatible with debiasing. Given that model bias arises due to the learning of bias features (\emph{i.e}., gender) that help target task optimization, we explore the following research question: \emph{Can we leverage shortcut features to replace the role of bias feature in target task optimization for debiasing?} To this end, we propose \emph{Shortcut Debiasing}, to first transfer the target task's learning of bias attributes from bias features to shortcut features, and then employ causal intervention to eliminate shortcut features during inference. The key idea of \emph{Shortcut Debiasing} is to design controllable shortcut features to on one hand replace bias features in contributing to the target task during the training stage, and on the other hand be easily removed by intervention during the inference stage. This guarantees the learning of the target task does not hinder the elimination of bias features. We apply \emph{Shortcut Debiasing} to several benchmark datasets, and achieve significant improvements over the state-of-the-art debiasing methods in both accuracy and fairness.

Linhui Xiao, Xiaoshan Yang, Xiangyuan Lan et al.

Visual Grounding, also known as Referring Expression Comprehension and Phrase Grounding, aims to ground the specific region(s) within the image(s) based on the given expression text. This task simulates the common referential relationships between visual and linguistic modalities, enabling machines to develop human-like multimodal comprehension capabilities. Consequently, it has extensive applications in various domains. However, since 2021, visual grounding has witnessed significant advancements, with emerging new concepts such as grounded pre-training, grounding multimodal LLMs, generalized visual grounding, and giga-pixel grounding, which have brought numerous new challenges. In this survey, we first examine the developmental history of visual grounding and provide an overview of essential background knowledge. We systematically track and summarize the advancements, and then meticulously define and organize the various settings to standardize future research and ensure a fair comparison. Additionally, we delve into numerous related datasets and applications, and highlight several advanced topics. Finally, we outline the challenges confronting visual grounding and propose valuable directions for future research, which may serve as inspiration for subsequent researchers. By extracting common technical details, this survey encompasses the representative work in each subtopic over the past decade. To the best of our knowledge, this paper represents the most comprehensive overview currently available in the field of visual grounding. This survey is designed to be suitable for both beginners and experienced researchers, serving as an invaluable resource for understanding key concepts and tracking the latest research developments. We keep tracing related work at https://github.com/linhuixiao/Awesome-Visual-Grounding.

Jingzhou Luo, Yang Liu, Weixing Chen et al.

3D Question Answering (3D QA) requires the model to comprehensively understand its situated 3D scene described by the text, then reason about its surrounding environment and answer a question under that situation. However, existing methods usually rely on global scene perception from pure 3D point clouds and overlook the importance of rich local texture details from multi-view images. Moreover, due to the inherent noise in camera poses and complex occlusions, there exists significant feature degradation and reduced feature robustness problems when aligning 3D point cloud with multi-view images. In this paper, we propose a Dual-vision Scene Perception Network (DSPNet), to comprehensively integrate multi-view and point cloud features to improve robustness in 3D QA. Our Text-guided Multi-view Fusion (TGMF) module prioritizes image views that closely match the semantic content of the text. To adaptively fuse back-projected multi-view images with point cloud features, we design the Adaptive Dual-vision Perception (ADVP) module, enhancing 3D scene comprehension. Additionally, our Multimodal Context-guided Reasoning (MCGR) module facilitates robust reasoning by integrating contextual information across visual and linguistic modalities. Experimental results on SQA3D and ScanQA datasets demonstrate the superiority of our DSPNet. Codes will be available at https://github.com/LZ-CH/DSPNet.

Ruihan Xu, Haokui Zhang, Yaowei Wang et al.

The growing use of deep learning necessitates efficient network design and deployment, making neural predictors vital for estimating attributes such as accuracy and latency. Recently, Graph Neural Networks (GNNs) and transformers have shown promising performance in representing neural architectures. However, each of both methods has its disadvantages. GNNs lack the capabilities to represent complicated features, while transformers face poor generalization when the depth of architecture grows. To mitigate the above issues, we rethink neural architecture topology and show that sibling nodes are pivotal while overlooked in previous research. We thus propose a novel predictor leveraging the strengths of GNNs and transformers to learn the enhanced topology. We introduce a novel token mixer that considers siblings, and a new channel mixer named bidirectional graph isomorphism feed-forward network. Our approach consistently achieves promising performance in both accuracy and latency prediction, providing valuable insights for learning Directed Acyclic Graph (DAG) topology. The code is available at https://github.com/XuRuihan/NNFormer.

Zhaozhi Wang, Tong Zhang, Mingyue Guo et al.

Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language alignment, yet they remain limited in visual-spatial reasoning. We first identify that this limitation arises from the attention mechanism: visual tokens are overshadowed by language tokens, preventing the model from consistently recognizing the same visual cues across frames. To address this challenge, we draw a novel connection between the self-expressiveness property in sparse subspace clustering and the attention mechanism in Transformers. Building on this insight, we propose VideoAnchor, a plug-and-play module that leverages subspace affinities to reinforce visual cues across frames without retraining, effectively anchoring attention to shared visual structures. Extensive experiments across benchmarks and backbone models show consistent performance gains -- $e.g.$, 3.2% and 4.6% improvements on VSI-Bench and Video-MME (spatial-related tasks) with InternVL2-8B and Qwen2.5VL-72B -- while qualitative analyses demonstrate more coherent subspace partitions and stronger visual grounding. Our codes will be made public available at https://github.com/feufhd/VideoAnchor.

Guiping Cao, Xiangyuan Lan, Wenjian Huang et al.

Popular transformer detectors have achieved promising performance through query-based learning using attention mechanisms. However, the roles of existing decoder query types (e.g., content query and positional query) are still underexplored. These queries are generally predefined with a fixed number (fixed-query), which limits their flexibility. We find that the learning of these fixed-query is impaired by Recurrent Opposing inTeractions (ROT) between two attention operations: Self-Attention (query-to-query) and Cross-Attention (query-to-encoder), thereby degrading decoder efficiency. Furthermore, "query ambiguity" arises when shared-weight decoder layers are processed with both one-to-one and one-to-many label assignments during training, violating DETR's one-to-one matching principle. To address these challenges, we propose DS-Det, a more efficient detector capable of detecting a flexible number of objects in images. Specifically, we reformulate and introduce a new unified Single-Query paradigm for decoder modeling, transforming the fixed-query into flexible. Furthermore, we propose a simplified decoder framework through attention disentangled learning: locating boxes with Cross-Attention (one-to-many process), deduplicating predictions with Self-Attention (one-to-one process), addressing "query ambiguity" and "ROT" issues directly, and enhancing decoder efficiency. We further introduce a unified PoCoo loss that leverages box size priors to prioritize query learning on hard samples such as small objects. Extensive experiments across five different backbone models on COCO2017 and WiderPerson datasets demonstrate the general effectiveness and superiority of DS-Det. The source codes are available at https://github.com/Med-Process/DS-Det/.

Guiping Cao, Wenjian Huang, Xiangyuan Lan et al.

Small Object Detection (SOD) poses significant challenges due to limited information and the model's low class prediction score. While Transformer-based detectors have shown promising performance, their potential for SOD remains largely unexplored. In typical DETR-like frameworks, the CNN backbone network, specialized in aggregating local information, struggles to capture the necessary contextual information for SOD. The multiple attention layers in the Transformer Encoder face difficulties in effectively attending to small objects and can also lead to blurring of features. Furthermore, the model's lower class prediction score of small objects compared to large objects further increases the difficulty of SOD. To address these challenges, we introduce a novel approach called Cross-DINO. This approach incorporates the deep MLP network to aggregate initial feature representations with both short and long range information for SOD. Then, a new Cross Coding Twice Module (CCTM) is applied to integrate these initial representations to the Transformer Encoder feature, enhancing the details of small objects. Additionally, we introduce a new kind of soft label named Category-Size (CS), integrating the Category and Size of objects. By treating CS as new ground truth, we propose a new loss function called Boost Loss to improve the class prediction score of the model. Extensive experimental results on COCO, WiderPerson, VisDrone, AI-TOD, and SODA-D datasets demonstrate that Cross-DINO efficiently improves the performance of DETR-like models on SOD. Specifically, our model achieves 36.4% APs on COCO for SOD with only 45M parameters, outperforming the DINO by +4.4% APS (36.4% vs. 32.0%) with fewer parameters and FLOPs, under 12 epochs training setting. The source codes will be available at https://github.com/Med-Process/Cross-DINO.

Jinpeng Wang, Tianci Luo, Yaohua Zha et al.

Visual In-Context Learning (VICL) enables adaptively solving vision tasks by leveraging pixel demonstrations, mimicking human-like task completion through analogy. Prompt selection is critical in VICL, but current methods assume the existence of a single "ideal" prompt in a pool of candidates, which in practice may not hold true. Multiple suitable prompts may exist, but individually they often fall short, leading to difficulties in selection and the exclusion of useful context. To address this, we propose a new perspective: prompt condensation. Rather than relying on a single prompt, candidate prompts collaborate to efficiently integrate informative contexts without sacrificing resolution. We devise Condenser, a lightweight external plugin that compresses relevant fine-grained context across multiple prompts. Optimized end-to-end with the backbone, Condenser ensures accurate integration of contextual cues. Experiments demonstrate Condenser outperforms state-of-the-arts across benchmark tasks, showing superior context compression, scalability with more prompts, and enhanced computational efficiency compared to ensemble methods, positioning it as a highly competitive solution for VICL. Code is open-sourced at https://github.com/gimpong/CVPR25-Condenser.

Niu Lian, Jun Li, Jinpeng Wang et al.

Self-Supervised Video Hashing (SSVH) compresses videos into hash codes for efficient indexing and retrieval using unlabeled training videos. Existing approaches rely on random frame sampling to learn video features and treat all frames equally. This results in suboptimal hash codes, as it ignores frame-specific information density and reconstruction difficulty. To address this limitation, we propose a new framework, termed AutoSSVH, that employs adversarial frame sampling with hash-based contrastive learning. Our adversarial sampling strategy automatically identifies and selects challenging frames with richer information for reconstruction, enhancing encoding capability. Additionally, we introduce a hash component voting strategy and a point-to-set (P2Set) hash-based contrastive objective, which help capture complex inter-video semantic relationships in the Hamming space and improve the discriminability of learned hash codes. Extensive experiments demonstrate that AutoSSVH achieves superior retrieval efficacy and efficiency compared to state-of-the-art approaches. Code is available at https://github.com/EliSpectre/CVPR25-AutoSSVH.

Lan Chen, Dong Li, Xiao Wang et al.

Existing event stream-based pattern recognition models usually represent the event stream as the point cloud, voxel, image, etc., and design various deep neural networks to learn their features. Although considerable results can be achieved in simple cases, however, the model performance may be limited by monotonous modality expressions, sub-optimal fusion, and readout mechanisms. In this paper, we propose a novel dual-stream framework for event stream-based pattern recognition via differentiated fusion, termed EFV++. It models two common event representations simultaneously, i.e., event images and event voxels. The spatial and three-dimensional stereo information can be learned separately by utilizing Transformer and Graph Neural Network (GNN). We believe the features of each representation still contain both efficient and redundant features and a sub-optimal solution may be obtained if we directly fuse them without differentiation. Thus, we divide each feature into three levels and retain high-quality features, blend medium-quality features, and exchange low-quality features. The enhanced dual features will be fed into the fusion Transformer together with bottleneck features. In addition, we introduce a novel hybrid interaction readout mechanism to enhance the diversity of features as final representations. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art performance on multiple widely used event stream-based classification datasets. Specifically, we achieve new state-of-the-art performance on the Bullying10k dataset, i.e., $90.51\%$, which exceeds the second place by $+2.21\%$. The source code of this paper has been released on \url{https://github.com/Event-AHU/EFV_event_classification/tree/EFVpp}.

Zheng Fang, Kangjun Liu, Ke Chen et al.

The task of radio map estimation aims to generate a dense representation of electromagnetic spectrum quantities, such as the received signal strength at each grid point within a geographic region, based on measurements from a subset of spatially distributed nodes (represented as pixels). Recently, deep vision models such as the U-Net have been adapted to radio map estimation, whose effectiveness can be guaranteed with sufficient spatial observations (typically 0.01% to 1% of pixels) in each map, to model local dependency of observed signal power. However, such a setting of sufficient measurements can be less practical in real-world scenarios, where extreme sparsity in spatial sampling can be widely encountered. To address this challenge, we propose RadioFormer, a novel multiple-granularity transformer designed to handle the constraints posed by spatial sparse observations. Our RadioFormer, through a dual-stream self-attention (DSA) module, can respectively discover the correlation of pixel-wise observed signal power and also learn patch-wise buildings' geometries in a style of multiple granularities, which are integrated into multi-scale representations of radio maps by a cross stream cross-attention (CCA) module. Extensive experiments on the public RadioMapSeer dataset demonstrate that RadioFormer outperforms state-of-the-art methods in radio map estimation while maintaining the lowest computational cost. Furthermore, the proposed approach exhibits exceptional generalization capabilities and robust zero-shot performance, underscoring its potential to advance radio map estimation in a more practical setting with very limited observation nodes.

Deng Li, Aming Wu, Yang Li et al.

In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and test data share the same distribution. To this end, continual test-time adaptation has attracted much attention, aiming to improve detectors' generalization by fine-tuning a few specific parameters, e.g., BatchNorm layers. However, based on a small number of test images, fine-tuning certain parameters may affect the representation ability of other fixed parameters, leading to performance degradation. Instead, we explore a new mechanism, i.e., converting the fine-tuning process to a specific-parameter generation. Particularly, we first design a dual-path LoRA-based domain-aware adapter that disentangles features into domain-invariant and domain-specific components, enabling efficient adaptation. Additionally, a conditional diffusion-based parameter generation mechanism is presented to synthesize the adapter's parameters based on the current environment, preventing the optimization from getting stuck in local optima. Finally, we propose a class-centered optimal transport alignment method to mitigate catastrophic forgetting. Extensive experiments conducted on various continuous domain adaptive object detection tasks demonstrate the effectiveness. Meanwhile, visualization results show that the representation extracted by the generated parameters can capture more object-related information and strengthen the generalization ability.

Yimin Zhou, Yichong Xia, Sicheng Pan et al.

With the increasing exploration and exploitation of the underwater world, underwater images have become a critical medium for human interaction with marine environments, driving extensive research into their efficient transmission and storage. However, contemporary underwater image compression algorithms fail to fully leverage the unique characteristics distinguishing underwater scenes from terrestrial images, resulting in suboptimal performance. To address this limitation, we introduce HQUIC, designed to exploit underwater-image-specific features for enhanced compression efficiency. HQUIC employs an ALTC module to adaptively predict the attenuation coefficients and global light information of the images, which effectively mitigates the issues caused by the differences in lighting and tone existing in underwater images. Subsequently, HQUIC employs a codebook as an auxiliary branch to extract the common objects within underwater images and enhances the performance of the main branch. Furthermore, HQUIC dynamically weights multi-scale frequency components, prioritizing information critical for distortion quality while discarding redundant details. Extensive evaluations on diverse underwater datasets demonstrate that HQUIC outperforms state-of-the-art compression methods.