In this paper, we propose a novel Joint framework for Deep Multi-view Clustering (DMJC), where multiple deep embedded features, multi-view fusion mechanism and clustering assignments can be learned simultaneously. Our key idea is that the joint learning strategy can sufficiently exploit clustering-friendly multi-view features and useful multi-view complementary information to improve the clustering performance. How to realize the multi-view fusion in such a joint framework is the primary challenge. To do so, we design two ingenious variants of deep multi-view joint clustering models under the proposed framework, where multi-view fusion is implemented by two different schemes. The first model, called DMJC-S, performs multi-view fusion in an implicit way via a novel multi-view soft assignment distribution. The second model, termed DMJC-T, defines a novel multi-view auxiliary target distribution to conduct the multi-view fusion explicitly. Both DMJC-S and DMJC-T are optimized under a KL divergence like clustering objective. Experiments on six challenging image datasets demonstrate the superiority of both DMJC-S and DMJC-T over single/multi-view baselines and the state-of-the-art multiview clustering methods, which proves the effectiveness of the proposed DMJC framework. To our best knowledge, this is the first work to model the multi-view clustering in a deep joint framework, which will provide a meaningful thinking in unsupervised multi-view learning.
Joint Learning of Self-Representation and Indicator for Multi-View Image Clustering
Nanjing University of Posts and Telecommunications(南京邮电大学);University of Trento(特伦托大学);Texas State University(得克萨斯州立大学);Wuhan University(武汉大学);Minjiang University(闽江学院)
Generalized Deep Multi-view Clustering via Causal Learning with Partially Aligned Cross-view Correspondence
College of Computer Science and Technology, National University of Defense Technology(计算机科学与技术学院,国防科技大学);Intelligent Game and Decision Lab(智能游戏与决策实验室);National University of Singapore(新加坡国立大学);Chinese PLA General Hospital(中国人民解放军总医院)
Robust Kernelized Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization
Fujian Key Laboratory of Sensing and Computing(福建省感知与计算重点实验室);State Key Laboratory of Intelligent Control for Smart City(智能城市智能控制国家重点实验室);School of Information Science and Management of Complex Systems and Engineering, Xiamen University(厦门大学信息科学与复杂系统与管理工程学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
Multi-level Reliable Guidance for Unpaired Multi-view Clustering
School of Mathematical Sciences, Nanjing Normal University(南京师范大学数学学院);School of Computer and Electronic Information, Nanjing Normal University(南京师范大学计算机与电子信息学院);School of Computing and Information Technology, University of Wollongong(沃林戈大学计算与信息科技学院)
Unified Multi-View Orthonormal Non-Negative Graph Based Clustering Framework
University of Melbourne(墨尔本大学);Monash University(莫纳什大学);University of New South Wales(新南威尔士大学);Northwestern Polytechnical University(西北工业大学);University of Texas at Arlington(德克萨斯大学阿灵顿分校)
Unpaired Multi-view Clustering via Reliable View Guidance
School of Mathematical Sciences, Nanjing Normal University(南京师范大学数学科学学院);School of Computer and Electronic Information, Nanjing Normal University(南京师范大学计算机与电子信息学院);School of Computing and Information Technology, University of Wollongong(伍伦贡大学计算与信息技术学院)
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);University of Chinese Academy of Sciences (UCAS)(中国科学院大学);Center for Research on Intelligent Perception and Computing, CASIA(中国科学院自动化研究所智能感知与计算研究中心);Department of Computer Science, University at Albany, SUNY(纽约州立大学奥尔巴尼分校计算机科学系)
Generative Diffusion Contrastive Network for Multi-View Clustering
Zhejiang Lab(浙江实验室);Hong Kong University of Science and Technology(香港科技大学);University of Science and Technology of China(中国科学技术大学);Huazhong University of Science and Technology(华中科技大学)
Straight-Path Flow Matching for Incomplete Multi-View Clustering
School of Software Engineering, Huazhong University of Science and Technology(华中科技大学软件工程学院);Australian Institute for Machine Learning, Adelaide University(澳大利亚机器学习研究所,阿德莱德大学);University of Auckland(奥克兰大学);University of New South Wales(新南威尔士大学);Communication University of China(中国通信大学)
Joint Adaptive Neighbours and Metric Learning for Multi-view Subspace Clustering
School of Information and Communication Engineering, Dalian University of Technology(大连理工大学信息与通信工程学院);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);University of Chinese Academy of Sciences (UCAS)(中国科学院大学)
One-Step Late Fusion Multi-view Clustering with Compressed Subspace
College of Computer, National University of Defense Technology(国防科技大学计算机学院);College of Intelligence Science and Technology, National University of Defense Technology(国防科技大学智能科学学院)
On Unifying Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Technology, Sydney(悉尼科技大学);The Hong Kong Polytechnic University(香港理工大学);Xiamen University(厦门大学)
Self-supervised Image Clustering from Multiple Incomplete Views via Constrastive Complementary Generation
College of Data Science and Application, Inner Mongolia University of Technology(内蒙古工业大学数据科学与应用学院);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);InnoPeak Technology, Inc(InnoPeak科技公司)
Consistent Multiple Graph Embedding for Multi-View Clustering
Institute of Information Science, Beijing Jiaotong University(北京交通大学信息科学研究所);Beijing Key Laboratory of Advanced Information Science and Network Technology(北京交通大学先进信息科学与网络技术北京重点实验室)
Deep Multi-View Semi-Supervised Clustering with Sample Pairwise Constraints
College of Information Science and Technology, Hainan University(海南大学信息科学技术学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Hainan University(海南大学)
R&D department ALTECA(阿尔泰卡公司研发部门);LIPN - CNRS UMR 7030 Sorbonne Paris Nord University(巴黎第十三大学(索邦巴黎北)法国国家科学研究中心UMR 7030实验室);ETIS - CNRS UMR 8051 CY Cergy Paris University(CY塞尔吉-巴黎大学法国国家科学研究中心UMR 8051实验室)
Towards Generalized Multi-stage Clustering: Multi-view Self-distillation
Nankai University(南开大学);Xingchuang Haihe Laboratory(兴创海河实验室);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Stony Brook University(石溪大学)
China University of Petroleum, Beijing(中国石油大学(北京))
本文提出了一种新的注意多视图深子空间网(Attentive Multi-View Deep Subspace Nets,AMVDSN),该网络深入挖掘多视图中潜在的一致性和视图特定信息,并通过考虑注意力机制获得的每个视图的动态贡献来融合它们。与大多数多视图子空间学习方法直接在原始数据上重建数据点或在深或浅空间中学习表示时只考虑一致性或互补性不同,我们提出的方法寻求找到一个联合潜在表示,该联合潜在表示显式地考虑多个视图之间的一致性和视图特定信息,然后对学习到的联合潜在表示进行子空间聚类。由于不同视角对表示学习的贡献不同,本文引入了注意力机制来获取每个视角的动态权重,在多视角子空间聚类中,该融合方法的性能优于以往的融合方法。由于神经网络的框架,该算法是直观的,可以很容易地优化,只需使用随机梯度下降(SGD),这也提供了强大的非线性表征能力相比,传统的子空间聚类方法。七个真实世界的数据集上的实验结果表明,我们提出的算法对一些国家的最先进的子空间学习方法的有效性。
Self-Supervised Discriminative Feature Learning for Deep Multi-View Clustering
School of Computer Science and Engineering, University of Electronic Science and Technology of China(计算机科学与工程学院,电子科技大学);School of Information and Communication Engineering, University of Electronic Science and Technology of China(信息与通信工程学院,电子科技大学);Department of Computer Science, University of Illinois at Chicago(计算机科学系,伊利诺伊大学芝加哥分校);Department of Computer Science and Engineering, Lehigh University(计算机科学与工程系,莱斯大学)
Mask-informed Deep Contrastive Incomplete Multi-view Clustering
Faculty of Data Science, City University of Macau(澳门城市大学数据科学学院);Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);School of Computer Science, China University of Geosciences(中国地质大学计算机学院)
University of Electronic Science and Technology of China(电子科技大学);Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province(四川省可信云计算与大数据重点实验室)
Deep Incomplete Multi-view Clustering with Distribution Dual-Consistency Recovery Guidance
School of Computer, National University of Defense Technology(国防科技大学计算机学院);Academy of Military Sciences(军事科学院);Chinese PLA General Hospital(中国人民解放军总医院)
College of Intelligence and Computing, Tianjin University(天津大学智能与计算学部);Haihe Lab of ITAI(海河人工智能与自主智能实验室);University at Albany, State University of New York(纽约州立大学奥尔巴尼分校)
Live and Learn: Continual Action Clustering with Incremental Views
School of Computer and Artificial Intelligence, Zhengzhou University(郑州大学计算机与人工智能学院);School of Creative Technologies, University of Portsmouth(朴茨茅斯大学创意技术学院)
Multiple Graph Learning for Scalable Multi-view Clustering
Xidian University(西安电子科技大学);School of Electronic Engineering, Xidian University(西安电子科技大学电子工程学院);Chongqing University of Posts and Telecommunications(重庆邮电大学)