Self-supervised Multi-view Clustering in Computer Vision: A Survey
Not on the map. Why?
Abstract (arXiv)
Multi-view clustering (MVC) has had significant implications in cross-modal representation learning and data-driven decision-making in recent years. It accomplishes this by leveraging the consistency and complementary information among multiple views to cluster samples into distinct groups. However, as contrastive learning continues to evolve within the field of computer vision, self-supervised learning has also made substantial research progress and is progressively becoming dominant in MVC methods. It guides the clustering process by designing proxy tasks to mine the representation of image and video data itself as supervisory information. Despite the rapid development of self-supervised MVC, there has yet to be a comprehensive survey to analyze and summarize the current state of research progress. Therefore, this paper explores the reasons and advantages of the emergence of self-supervised MVC and discusses the internal connections and classifications of common datasets, data issues, representation learning methods, and self-supervised learning methods. This paper does not only introduce the mechanisms for each category of methods but also gives a few examples of how these techniques are used. In the end, some open problems are pointed out for further investigation and development.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 54 of its 123 references that are in the map. First posted on arXiv 18 Sep 2023.
Builds on
54 of 123 references.
References · 54
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2022Generative Adversarial Networkscited by 5,603
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
- 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
- 2020Self-supervised Learning: Generative or Contrastivecited by 693
- 2020Contrastive Multi-View Representation Learning on Graphscited by 651
- 2018Understanding disentangling in β-VAEcited by 332
- 2019Self-Supervised Learning by Cross-Modal Audio-Video Clusteringcited by 264
38 more
- 2016Variational Deep Embedding: An Unsupervised and Generative Approach to Clusteringcited by 219
- 2020Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDcited by 212
- 2020A Review on Generative Adversarial Networks: Algorithms, Theory, and Applicationscited by 209
- 2018Multimodal Generative Models for Scalable Weakly-Supervised Learningcited by 200
- 2020Learning Robust Representations via Multi-View Information Bottleneckcited by 189
- 2016On Deep Multi-View Representation Learning: Objectives and Optimizationcited by 162
- 2021SPICE: Semantic Pseudo-labeling for Image Clusteringcited by 104
- 2016Joint Multimodal Learning with Deep Generative Modelscited by 87
- 2021Multi-view Contrastive Graph Clusteringcited by 76
- 2021Multi-level Feature Learning for Contrastive Multi-view Clusteringcited by 73
- 2021Reconsidering Representation Alignment for Multi-view Clusteringcited by 57
- 2021Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clusteringcited by 51
- 2021Self-Supervised Discriminative Feature Learning for Deep Multi-View Clusteringcited by 41
- 2017VIGAN: Missing View Imputation with Generative Adversarial Networkscited by 33
- 2023Deep Multiview Clustering by Contrasting Cluster Assignmentscited by 33
- 2019Self-Supervised Convolutional Subspace Clustering Networkcited by 32
- 2018Deep Multimodal Subspace Clustering Networkscited by 31
- 2020Deep Embedded Multi-view Clustering with Collaborative Trainingcited by 31
- 2022A Survey on Incomplete Multi-view Clusteringcited by 31
- 2014Histogram of Oriented Principal Components for Cross-View Action Recognitioncited by 27
- 2017Multi-View Image Generation from a Single-Viewcited by 27
- 2019Multi-graph Fusion for Multi-view Spectral Clusteringcited by 27
- 2020Generative Partial Multi-View Clusteringcited by 25
- 2019Multi-view Deep Subspace Clustering Networkscited by 24
- 2023Decoupled Contrastive Multi-View Clustering with High-Order Random Walkscited by 23
- 2023Incomplete Multi-view Clustering via Prototype-based Imputationcited by 21
- 2022Contrastive Multi-view Hyperbolic Hierarchical Clusteringcited by 19
- 2023Unpaired Multi-View Graph Clustering with Cross-View Structure Matchingcited by 19
- 2019Shared Generative Latent Representation Learning for Multi-view Clusteringcited by 17
- 2022Self-Supervised Information Bottleneck for Deep Multi-View Subspace Clusteringcited by 15
- 2023Deep Multi-View Subspace Clustering with Anchor Graphcited by 13
- 2023MUSE: Multi-View Contrastive Learning for Heterophilic Graphscited by 13
- 2020Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labelingcited by 12
- 2023Semantic Invariant Multi-view Clustering with Fully Incomplete Informationcited by 12
- 2019Multi-View Multiple Clusterings using Deep Matrix Factorizationcited by 9
- 2019MEGAN: A Generative Adversarial Network for Multi-View Network Embeddingcited by 8
- 2022Self-supervised Image Clustering from Multiple Incomplete Views via Constrastive Complementary Generationcited by 8
- 2022Multi-View Clustering for Open Knowledge Base Canonicalizationcited by 5
50 most cited of 54 All 54 (JSON)
Built on by
Citing papers per year: 2024: 1.
1 paper.