论文检索

Feifei Qian, Lu Bai, Lixin Cui, Ming Li, Hangyuan Du, Yue Wang, Edwin Hancock

The over-smoothing has emerged as a major challenge in the development of Graph Neural Networks (GNNs). While existing state-of-the-art methods effectively mitigate the diminishing distance between nodes and improve the performance of node classification, they tend to be elusive for graph-level tasks. This paper introduces a novel entropy-based perspective to explore the over-smoothing problem, simultaneously enhancing the distinguishability of non-isomorphic graphs. We provide a theoretical analysis of the relationship between the smoothness and the entropy for graphs, highlighting how the over-smoothing in high-entropic regions negatively impact the graph classification performance. To tackle this issue, we propose a simple yet effective method to Sample and Discretize node features in high-Entropic regions (SDE), aiming to preserve the critical and complicated structural information. Moreover, we introduce a new evaluation metric to assess the over-smoothing for graph-level tasks, focusing on node distributions. Experimental results demonstrate that the proposed SDE method significantly outperforms existing state-of-the-art methods, establishing a new benchmark in the field of GNNs.

Jiafan Li, Jiaqi Zhu, Liang Chang, Yilin Li, Miaomiao Li, Yang Wang, Yi Yang, Hongan Wang

Nowadays, numerous online platforms can be described as multi-modal heterogeneous networks (MMHNs), such as Douban's movie networks and Amazon's product review networks. Accurately categorizing nodes within these networks is crucial for analyzing the corresponding entities, which requires effective representation learning on nodes. However, existing multi-modal fusion methods often adopt either early fusion strategies which may lose the unique characteristics of individual modalities, or late fusion approaches overlooking the cross-modal guidance in GNN-based information propagation. In this paper, we propose a novel model for node classification in MMHNs, named Heterogeneous Graph Neural Network with Inter-Modal Attention (HGNN-IMA). It learns node representations by capturing the mutual influence of multiple modalities during the information propagation process, within the framework of heterogeneous graph transformer. Specifically, a nested inter-modal attention mechanism is integrated into the inter-node attention to achieve adaptive multi-modal fusion, and modality alignment is also taken into account to encourage the propagation among nodes with consistent similarities across all modalities. Moreover, an attention loss is augmented to mitigate the impact of missing modalities. Extensive experiments validate the superiority of the model in the node classification task, providing an innovative view to handle multi-modal data, especially when accompanied with network structures. The full version including Appendix is available at http://arxiv.org/abs/2505.07895.

Lei Hu, Zhiyong Gan, Ling Deng, Jinglin Liang, Lingyu Liang, Shuangping Huang, Tianshui Chen

Continual Anomaly Detection (CAD) enables anomaly detection models in learning new classes while preserving knowledge of historical classes. CAD faces two key challenges: catastrophic forgetting and segmentation of small anomalous regions. Existing CAD methods store image distributions or patch features to mitigate catastrophic forgetting, but they fail to preserve pixel-level detailed features for accurate segmentation. To overcome this limitation, we propose ReplayCAD, a novel diffusion-driven generative replay framework that replay high-quality historical data, thus effectively preserving pixel-level detailed features. Specifically, we compress historical data by searching for a class semantic embedding in the conditional space of the pre-trained diffusion model, which can guide the model to replay data with fine-grained pixel details, thus improving the segmentation performance. However, relying solely on semantic features results in limited spatial diversity. Hence, we further use spatial features to guide data compression, achieving precise control of sample space, thereby generating more diverse data. Our method achieves state-of-the-art performance in both classification and segmentation, with notable improvements in segmentation: 11.5% on VisA and 8.1% on MVTec. Our source code is available at https://github.com/HULEI7/ReplayCAD.

Xiaobin Hong, Mingkai Lin, Xiangkai Ma, Wenzhong Li, Sanglu Lu

Graph Neural Networks (GNNs) have demonstrated remarkable effectiveness across various tasks but are often hindered by their high computational overhead. GNN-to-MLP distillation provides a promising remedy by transferring knowledge from complex GNNs to lightweight MLPs. However, existing methods largely overlook the differences in aggregation mechanisms and heterogeneous architectures. Simplifying such intricate information into MLP potentially causes information loss or distortion, ultimately resulting in suboptimal performance. This paper proposes an aggregation mechanism enhanced GNN distillation framework (AMEND). AMEND introduces multi-scope aggregation context preservation to replicate the teacher's broad aggregation scopes and an aggregation-enhanced centered kernel alignment method to match the teacher's aggregation patterns. To ensure efficient and robust knowledge transfer, we integrate a manifold mixup strategy, enabling the student to capture the teacher's insights into mixed data distributions. Experimental results on 8 standard and 4 large-scale datasets demonstrate that AMEND consistently outperforms state-of-the-art distillation methods.

Bingdao Feng, Di Jin, Xiaobao Wang, Dongxiao He, Jingyi Cao, Zhen Wang

Defending against adversarial attacks on graphs has become increasingly important. Graph refinement to enhance the quality and robustness of representation learning is a critical area that requires thorough investigation. We observe that representations learned from attacked graphs are often ineffective for refinement due to perturbations that cause the endpoints of perturbed edges to become more similar, complicating the defender's ability to distinguish them. To address this challenge, we propose a robust unsupervised graph learning framework that utilizes cleaner graphs to learn effective representations. Specifically, we introduce an anomaly detection model based on contrastive learning to obtain a rough graph excluding a large number of perturbed structures. Subsequently, we then propose the Graph Pollution Degree (GPD), a mutual information-based measure that leverages the encoder's representation capability on the rough graph to assess the trustworthiness of the predicted graph and refine the learned representations. Extensive experiments on four benchmark datasets demonstrate that our method outperforms nine state-of-the-art defense models, effectively defending against adversarial attacks and enhancing node classification performance.

Lu Bai, Feifei Qian, Lixin Cui, Ming Li, Hangyuan Du, Yue Wang, Edwin Hancock

In this paper, we propose a new model to learn Adaptive Kernel-based Representations (AKBR) for graph classification. Unlike state-of-the-art R-convolution graph kernels that are defined by merely counting any pair of isomorphic substructures between graphs and cannot provide an end-to-end learning mechanism for the classifier, the proposed AKBR approach aims to define an end-to-end representation learning model to construct an adaptive kernel matrix for graphs. To this end, we commence by leveraging a novel feature-channel attention mechanism to capture the interdependencies between different substructure invariants of original graphs. The proposed AKBR model can thus effectively identify the structural importance of different substructures, and compute the R-convolution kernel between pairwise graphs associated with the more significant substructures specified by their structural attentions. Furthermore, the proposed AKBR model employs all sample graphs as the prototype graphs, naturally providing an end-to-end learning architecture between the kernel computation as well as the classifier. Experimental results show that the proposed AKBR model outperforms existing state-of-the-art graph kernels and deep learning methods on standard graph benchmarks.

Haolong Xiang, Xiaolong Xu, Guangdong Wang, Xuyun Zhang, Xiaoyong Li, Qi Zhang, Amin Beheshti, Wei Fan

With the rapid urbanization in the modern era, smart traffic profiling based on multimodal sources of data has been playing a significant role in ensuring safe travel, reducing traffic congestion and optimizing urban mobility. Most existing methods for traffic profiling on the road level usually utilize single-modality data, i.e., they mainly focus on image processing with deep vision models or auxiliary analysis on the textual data. However, the joint modeling and multimodal fusion of the textual and visual modalities have been rarely studied in road traffic profiling, which largely hinders the accurate prediction or classification of traffic conditions. To address this issue, we propose a novel multimodal learning and fusion framework for road traffic profiling, named TraffiCFUS. Specifically, given the traffic images, our TraffiCFUS framework first introduces Vision Language Models (VLMs) to generate text and then creates tailored prompt instructions for refining this text according to the specific scene requirements of road traffic profiling. Next, we apply the discrete Fourier transform to convert multimodal data from the spatial domain to the frequency domain and perform a cross-modal spectrum transform to filter out irrelevant information for traffic profiling. Furthermore, the processed spatial multimodal data is combined to generate fusion loss and interaction loss with contrastive learning. Finally, extensive experiments on four real-world datasets illustrate superior performance compared with the state-of-the-art approaches.

Florent Avellaneda

Decision trees are widely used in machine learning for their interpretability and effectiveness in classification tasks. Traditional axis-parallel decision trees partition data using single-feature thresholds at each node, but they often struggle to represent complex, non-axis-aligned decision boundaries efficiently. This limitation can result in unnecessarily large and less interpretable trees. Oblique decision trees address this limitation by using linear combinations of features at each node, allowing a more natural representation of complex decision boundaries while maintaining interpretability through sparse linear combinations. However, learning optimal oblique decision trees poses a significant computational challenge, as existing methods predominantly rely on suboptimal greedy heuristics. In this paper, we propose a novel approach to learning globally optimal oblique decision trees by reformulating the problem as a (Max)SAT instance. By leveraging state-of-the-art (Max)SAT solvers, our method efficiently explores the solution space to identify optimal trees. Experiments on benchmark datasets demonstrate that our approach generates optimal oblique decision trees within reasonable computational time for small to medium-sized datasets.

Zhikang Zhao, Kaitao Chen, Jing Zhao

Whole slide images (WSIs) are gigapixel digital scans of traditional pathology slides, offering substantial support for cancer diagnosis. Current multiple instance learning (MIL) methods for WSIs typically extract instance features and aggregate these into a single bag feature for prediction. We observe that these MIL methods rely on point estimation, where each bag is mapped to a deterministic embedding. Such MIL methods based on point estimation fail to capture the full spectrum of data variability due to the reliance on fixed embedding, especially when the number of trainable bags is limited. In this paper, we rethink probabilistic modeling in MIL and propose RPMIL, an uncertainty-aware probabilistic MIL method for whole slide pathology diagnosis. RPMIL learns a probabilistic aggregator to consolidate instance features into dynamic bag feature distributions instead of a deterministic bag feature. Specifically, we employ a variational autoencoder approach to compress multiple instance features into a low-dimension space with probabilistic representation and obtain the bag feature distribution formulated by the mean and variance. Furthermore, we drive the prediction by jointly leveraging the instance feature distribution and bag feature distribution. We evaluate the WSI classification performance on two public datasets: Camelyon16 and TCGA-NSCLC. Extensive experiments demonstrate that our method surpasses point estimation methods in MIL, achieving state-of-the-art levels.

Tengyu Zhang, Deyu Zeng, Baoqiang Li, Wei Wang, Wei Liu, Zongze Wu

Anomaly detection plays a pivotal role in industrial quality assurance processes, with cross-domain problems, exemplified by the model upgrade from RGB to 3D, being prevalent in real-world scenarios yet remaining systematically underexplored. To address the severe challenges posed by the extreme lack of datasets in target domain, we retain the knowledge from source models and explore a novel solution for anomaly detection through cross-domain learning, introducing HyperTrans. Targeting few-shot scenarios, HyperTrans centers around hypergraphs to model the relationship of the limited patch features and employs a perturbation-rectification-scoring architecture. The domain perturbation module injects and adapts channel-level statistical perturbations, mitigating style shifts during domain transfer. Subsequently, a residual hypergraph restoration module utilizes a cross-domain hypergraph to capture higher-order correlations in patches and align them across domains. Ultimately, with feature patterns exhibiting reduced domain shifts, an inter-domain scoring module aggregates similarity information between patches and normal patterns within the multi-domain subhypergraphs to make an integrated decision, generating multi-level anomaly predictions. Extensive experiments demonstrate that HyperTrans offers significant advantages in anomaly classification and anomaly segmentation tasks, outperforming state-of-the-art non-cross-domain methods in image-wise ROCAUC by 13%, 12%, and 15% in 1-shot, 2-shot, and 5-shot settings on MVTec3D AD.

Yufei Yin, Lechao Cheng, Wengang Zhou, Jiajun Deng, Zhou Yu, Houqiang Li

In recent years, weakly supervised object detection (WSOD) has attracted much attention due to its low labeling cost. The success of recent WSOD models is often ascribed to the two-stage multi-class classification (MCC) task, i.e., multiple instance learning and online classification refinement. Despite achieving non-trivial progresses, these methods overlook potential classification ambiguities between these two MCC tasks and fail to leverage their unique strengths. In this work, we introduce a novel WSOD framework to ameliorate these two issues. For one thing, we propose a self-classification enhancement module that integrates intra-class binary classification (ICBC) to bridge the gap between the two distinct MCC tasks. The ICBC task enhances the network’s discrimination between positive and mis-located samples in a class-wise manner and forges a mutually reinforcing relationship with the MCC task. For another, we propose a self-classification correction algorithm during inference, which combines the results of both MCC tasks to effectively reduce the mis-classified predictions. Extensive experiments on the prevalent VOC 2007 & 2012 datasets demonstrate the superior performance of our framework.

Yufei Yang, Song Xiao, Lixiang Li, Wenqian Dong, Jiahui Qu

Due to the high cost of data collection and training, the well-performed hyperspectral image (HSI) classification models are of great value and vulnerable to piracy threat during transmission and use. Model watermarking is a promising technology for intellectual property (IP) protection of models. However, the existing model watermarking methods for RGB image classification models ignore the complexity of ground objects and high dimension of HSIs, which makes trigger samples easy to be detected and forged. To address this problem, we propose a signature diffusion embedded dual-verification watermarking method, which generates imperceptible trigger samples with explicit owner information to achieve dual verification of both model ownership and legality of trigger set. Specifically, the subpixel-space owner signature diffusion incorporated imperceptible trigger set generation method is proposed to manipulate owner signature incorporated to the abundance matrix of seeds via diffusion model in subpixel space, thus balancing the perceptual quality of trigger samples and signature extraction capability. To resist ownership confusion, dual-stamp ownership verification is proposed to query the suspicious model with trigger samples for ownership verification, and further extracts signature from trigger samples to guarantee their legality. Extensive experiments demonstrate the proposed method can effectively protect IP of HSI classification models.

Yueguang Yang, Jiahui Qu, Ling Huang, Wenqian Dong

Multimodal remote sensing image classification (RSIC) has emerged as a key focus in Earth observation, driven by its capacity to extract complementary information from diverse sources. Existing methods struggle with modality absence caused by weather or equipment failures, leading to performance degradation. As a solution, knowledge distillation-based methods train student networks (SN) using a full-modality teacher, but they usually require training separate SN for each modality absence scenario, increasing complexity. To this end, we propose a unified Distillation Prompt Mamba (DPMamba) framework for multimodal RSIC with missing modalities. DPMamba leverages knowledge distillation in a shared text semantic space to optimize learnable prompts, transforming them from ``placeholder" to ``adaptation" states by enriching missing modality information with full-modality knowledge. To achieve this, we focus on two main aspects: first, we propose a new modality-aware Mamba for dynamically and hierarchically extracting cross-modality interactive features, providing richer, contextually relevant representations for backpropagation-based optimization of prompts; and second, we introduce a novel text-bridging distillation method to efficiently transfer full-modality knowledge, guiding the inclusion of missing modality information into prompts. Extensive evaluations demonstrate the effectiveness and robustness of the proposed DPMamba.

Rui Yan, Jin Wang, Hongyu Qu, Xiaoyu Du, Dong Zhang, Jinhui Tang, Tieniu Tan

Recently, adapting Vision Language Models (VLMs) to zero-shot visual classification by tuning class embedding with a few prompts (Test-time Prompt Tuning, TPT) or replacing class names with generated visual samples (support-set) has shown promising results. However, TPT cannot avoid the semantic gap between modalities while the support-set cannot be tuned. To this end, we draw on each other's strengths and propose a novel framework, namely TEst-time Support-set Tuning for zero-shot Video Classification (TEST-V). It first dilates the support-set with multiple prompts (Multi-prompting Support-set Dilation, MSD) and then erodes the support-set via learnable weights to mine key cues dynamically (Temporal-aware Support-set Erosion, TSE). Specifically, i) MSD expands the support samples for each class based on multiple prompts inquired from LLMs to enrich the diversity of the support-set. ii) TSE tunes the support-set with factorized learnable weights according to the temporal prediction consistency in a self-supervised manner to dig pivotal supporting cues for each class. TEST-V achieves state-of-the-art results across four benchmarks and shows good interpretability.

Wei Wei, Zixiong Li, Jing Yan, Mingwen Shao, Lin Li

Domain generalization (DG) aims to train models on multiple source domains to generalize effectively to unseen target domains, addressing performance degradation caused by domain shifts. Many existing methods rely on direct feature alignment, which disrupts natural sequence relationships, causes misalignment and feature distortion, and leads to overfitting, especially with significant domain gaps. To tackle these issues, we propose a novel DG approach with two key modules: the Sample Difference Keeping (SDK) module, which preserves natural sequence relationships to enhance feature diversity and separability, and the Sample Consistency Alignment (SCA) module, which achieves indirect alignment by modeling inter-class and inter-domain relationship consistencies. This approach mitigates overfitting and misalignment, ensuring adaptability to significant domain gaps. Extensive experiments demonstrate that our framework consistently outperforms state-of-the-art methods.

Yue Wang, Shuai Xu, Xuelin Zhu, Yicong Li

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen state-object combinations by leveraging known combinations. Existing studies basically rely on the cross-modal alignment capabilities of CLIP but tend to overlook its limitations in capturing fine-grained local features, which arise from its architectural and training paradigm. To address this issue, we propose a Multi-Stage Cross-modal Interaction (MSCI) model that effectively explores and utilizes intermediate-layer information from CLIP's visual encoder. Specifically, we design two self-adaptive aggregators to extract local information from low-level visual features and integrate global information from high-level visual features, respectively. These key information are progressively incorporated into textual representations through a stage-by-stage interaction mechanism, significantly enhancing the model’s perception capability for fine-grained local visual information. Additionally, MSCI dynamically adjusts the attention weights between global and local visual information based on different combinations, as well as different elements within the same combination, allowing it to flexibly adapt to diverse scenarios. Experiments on three widely used datasets fully validate the effectiveness and superiority of the proposed model. Data and code are available at https://github.com/ltpwy/MSCI.

Yongqi Wang, Xinxiao Wu, Shuo Yang

Open-vocabulary video visual relationship detection aims to detect objects and their relationships in videos without being restricted by predefined object or relationship categories. Existing methods leverage the rich semantic knowledge of pre-trained vision-language models such as CLIP to identify novel categories. They typically adopt a cascaded pipeline to first detect objects and then classify relationships based on the detected objects, which may lead to error propagation and thus suboptimal performance. In this paper, we propose Mutual EnhancemenT of Objects and Relationships (METOR), a query-based unified framework to jointly model and mutually enhance object detection and relationship classification in open-vocabulary scenarios. Under this framework, we first design a CLIP-based contextual refinement encoding module that extracts visual contexts of objects and relationships to refine the encoding of text features and object queries, thus improving the generalization of encoding to novel categories. Then we propose an iterative enhancement module to alternatively enhance the representations of objects and relationships by fully exploiting their interdependence to improve recognition performance. Extensive experiments on two public datasets, VidVRD and VidOR, demonstrate that our framework achieves state-of-the-art performance. Codes are at https://github.com/wangyongqi558/METOR.

Xiaxin Wang, Haoyu Cai, Xiaobo Shen, Xia Wu

Conventional image set methods typically learn from image sets stored in a single location. However, in real-world applications, image sets are often distributed across different locations. Learning from such distributed sets using deep neural networks poses challenges for efficient image set classification and retrieval. To address this, we propose Distributed Cascade Manifold Hashing Network (DCMHN) for compact image set representation. DCMHN represents each image set using an SPD manifold and utilizes a manifold hashing network to generate hash codes, enabling efficient classification and retrieval. The network is trained in a cascaded manner, where the bilinear mapping in the BiMap layer is learned first, followed by joint learning of the hash function and classifier in the hash layer. DCMHN enforces local consistency on global variables across neighboring nodes, allowing parallel optimization. Extensive experiments on three benchmark image set datasets demonstrate that the proposed DCMHN achieves competitive accuracies in distributed settings, and outperforms state-of-the-arts in terms of computation and storage efficiency.

Haoming Luo, Xiaotian Yu, Shengxuming Zhang, Jiabin Xia, Jian Yang, Yuning Sun, Xiuming Zhang, Jing Zhang, Zunlei Feng

Pathology images are considered the ``gold standard" for cancer diagnosis and treatment, with gigapixel images providing extensive tissue and cellular information. Existing methods fail to simultaneously extract global structural and local detail features for comprehensive pathology image analysis efficiently. To address these limitations, we propose a self-calibration enhanced framework for whole slide pathology image analysis, comprising three components: a global branch, a focus predictor, and a detailed branch. The global branch initially classifies using the pathological thumbnail, while the focus predictor identifies relevant regions for classification based on the last layer features of the global branch. The detailed extraction branch then assesses whether the magnified regions correspond to the lesion area. Finally, a feature consistency constraint between the global and detail branches ensures that the global branch focuses on the appropriate region and extracts sufficient discriminative features for final identification. These focused discriminative features can facilitate the discovery of novel prognostic tumor markers, from the perspective of feature uniqueness and tissue spatial distribution. Extensive experiment results demonstrate that the proposed framework can rapidly deliver accurate and explainable results for pathological grading and prognosis tasks.

Feng Luan, Jiarui Hu, Changshi Zhou, Zhipeng Wang, Jiguang Yue, Yanmin Zhou, Bin He

Point cloud classification is critical for three-dimensional scene understanding. However, in real-world scenarios, depth cameras often capture partial, single-view point clouds of objects with different poses, making their accurate classification a challenge. In this paper, we propose a novel point cloud classification network that captures the detailed spatial structure of objects by constructing tetrahedra, which is different from point-wise operations. Specifically, we propose a RISpaNet block to extract rotation-invariant features. A rotation-invariant property generation module is designed in RISpaNet for constructing rotation-invariant tetrahedron properties (RITPs). Meanwhile, a multi-scale pooling module and a hybrid encoder are used to process RITPs to generate integrated rotation-invariant features. Further, for single-view point clouds, a complete point cloud auxiliary branch and a part-whole correlation module are jointly employed to obtain complete point cloud features from partial point clouds. Experimental results show that this network performs better than other state-of-the-art methods, evaluated on four public datasets. We achieved an overall accuracy of 94.7% (+2.0%) on ModelNet40, 93.4% (+5.9%) on MVP, 94.7% (+6.3%) on PCN and 94.8% (+1.7%) on ScanObjectNN. Our project website is https://luxurylf.github.io/RISpaNet_project/.