Quality-Aware Robust Multi-View Clustering for Heterogeneous Observation Noise
School of Software Technology, Zhejiang University(浙江大学软件技术学院);School of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);School of Computer Science(计算机科学学院)
Peihan Wu, Guanjie Cheng, Yufei Tong, Meng Xi, Shuiguang Deng
Deep multi-view clustering has achieved remarkable progress but remains vulnerable to complex noise in real-world applications. Existing noisy robust methods predominantly rely on a simplified binary assumption, treating data as either perfectly clean or completely corrupted. This overlooks the prevalent existence of heterogeneous observation noise, where contamination intensity varies continuously across data. To bridge this gap, we propose a novel framework termed Quality-Aware Robust Multi-View Clustering (QARMVC). Specifically, QARMVC employs an information bottleneck mechanism to extract intrinsic semantics for view reconstruction. Leveraging the insight that noise disrupts semantic integrity and impedes reconstruction, we utilize the resulting reconstruction discrepancy to precisely quantify fine-grained contamination intensity and derive instance-level quality scores. These scores are integrated into a hierarchical learning strategy: at the feature level, a quality-weighted contrastive objective is designed to adaptively suppress the propagation of noise; at the fusion level, a high-quality global consensus is constructed via quality-weighted aggregation, which is subsequently utilized to align and rectify local views via mutual information maximization. Extensive experiments on five benchmark datasets demonstrate that QARMVC consistently outperforms state-of-the-art baselines, particularly in scenarios with heterogeneous noise intensities.
College of Mathematics and Informatics, South China Agricultural University(华南农业大学数学与信息学院);Key Laboratory of Smart Agricultural Technology in Tropical South China, Ministry of Agriculture and Rural Affairs(农业农村部华南热带智慧农业技术重点实验室);School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机学院)
Unsupervised Video Person Re-identification via Noise and Hard frame Aware Clustering
Wuhan University of Science and Technology(武汉科技大学);Research Institute for an Inclusive Society through Engineering (RIISE), The University of Tokyo(东京大学包容性社会工程研究所(RIISE));The University of Tokyo(东京大学)
Key Laboratory for Information Science of Electromagnetic Waves, Ministry of Education, Fudan University(复旦大学电磁波信息科学教育部重点实验室);Discipline and Technology Center of Microwave Vision Intelligent Sensing, Fudan University(复旦大学微波视觉智能感知学科与技术中心)
HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning
Southern University of Science and Technology(南方科技大学);Zhejiang University(浙江大学);Technical University of Munich(慕尼黑工业大学);City University of Hong Kong(香港城市大学);Shanghai Jiao Tong University(上海交通大学)
Styleverse: Towards Identity Stylization across Heterogeneous Domains
National Laboratory of Pattern Recognition, CASIA(中国科学院自动化研究所模式识别国家重点实验室);Center for Excellence in Brain Science and Intelligence Technology, CAS(中国科学院脑科学与智能技术卓越创新中心);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
Context-Aware Hypergraph Construction for Robust Spectral Clustering
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);The University of Adelaide(阿德莱德大学);State University of New York, Binghamton(纽约州立大学宾汉姆顿分校)
Scalable Context-Preserving Model-Aware Deep Clustering for Hyperspectral Images
Ghent University(根特大学);Royal Institute for Cultural Heritage (KIK-IRPA)(皇家文化遗产研究院);China University of Geosciences(中国地质大学);Vrije Universiteit Brussel(布鲁塞尔自由大学)
Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalities
SenseTime Research(商汤科技研究院);The University of Sydney(悉尼大学);University of Cologne(科隆大学);EWI gGmbH(EWI有限责任公司);Shanghai AI Laboratory(上海人工智能实验室);Qing Yuan Research Institute of Shanghai Jiao Tong University(上海交通大学清源研究院)