mlsanityData to 7 Oct 2026

Contrastive Clustering

arXiv 2009.09687 ↗First posted 21 Sep 2020cs.LG cs.CV stat.MLcited by 264

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a one-stage online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning. To be specific, for a given dataset, the positive and negative instance pairs are constructed through data augmentations and then projected into a feature space. Therein, the instance- and cluster-level contrastive learning are respectively conducted in the row and column space by maximizing the similarities of positive pairs while minimizing those of negative ones. Our key observation is that the rows of the feature matrix could be regarded as soft labels of instances, and accordingly the columns could be further regarded as cluster representations. By simultaneously optimizing the instance- and cluster-level contrastive loss, the model jointly learns representations and cluster assignments in an end-to-end manner. Extensive experimental results show that CC remarkably outperforms 17 competitive clustering methods on six challenging image benchmarks. In particular, CC achieves an NMI of 0.705 (0.431) on the CIFAR-10 (CIFAR-100) dataset, which is an up to 19% (39%) performance improvement compared with the best baseline.

Key facts. Cited by 264 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 32; 2022: 55; 2023: 66; 2024: 45; 2025: 40; 2026: 26.

264 papers.

Sort:

By area:

  1. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  2. 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
  3. 2023TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Seriescited by 165
  4. 2022Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learningcited by 159
  5. 2021From Canonical Correlation Analysis to Self-supervised Graph Neural Networkscited by 138
  6. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  7. 2021SPICE: Semantic Pseudo-labeling for Image Clusteringcited by 104
  8. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
  9. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 93
  10. 2021Multi-view Contrastive Graph Clusteringcited by 76
  11. 2021Multi-level Feature Learning for Contrastive Multi-view Clusteringcited by 73
  12. 2022A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directionscited by 73
38 more
  1. 2022NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenescited by 71
  2. 2021Graph Contrastive Clusteringcited by 61
  3. 2022Patch-level Representation Learning for Self-supervised Vision Transformerscited by 60
  4. 2021Learning Representation for Clustering via Prototype Scattering and Positive Samplingcited by 58
  5. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  6. 2022Neural Manifold Clustering and Embeddingcited by 44
  7. 2022HCSC: Hierarchical Contrastive Selective Codingcited by 43
  8. 2021You Never Cluster Alonecited by 38
  9. 2023Image Clustering with External Guidancecited by 36
  10. 2021Contrastive Learning for Fair Representationscited by 34
  11. 2023Deep Multiview Clustering by Contrasting Cluster Assignmentscited by 33
  12. 2022Towards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margincited by 32
  13. 2022Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesiscited by 31
  14. 2021A Practical Contrastive Learning Framework for Single-Image Super-Resolutioncited by 30
  15. 2022SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognitioncited by 29
  16. 2022Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embeddingcited by 28
  17. 2022MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Seriescited by 28
  18. 2022Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Datacited by 27
  19. 2024Heterogeneous Contrastive Learning for Foundation Models and Beyondcited by 27
  20. 2023Subclass-balancing Contrastive Learning for Long-tailed Recognitioncited by 26
  21. 2022Semantic-Enhanced Image Clusteringcited by 25
  22. 2022Making Your First Choice: To Address Cold Start Problem in Vision Active Learningcited by 25
  23. 2022Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Workscited by 24
  24. 2023Stable Cluster Discrimination for Deep Clusteringcited by 24
  25. 2021Clustering by Maximizing Mutual Information Across Viewscited by 23
  26. 2023Clustering based Point Cloud Representation Learning for 3D Analysiscited by 23
  27. 2023Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Modelscited by 22
  28. 2022GLCC: A General Framework for Graph-Level Clusteringcited by 21
  29. 2023Incomplete Multi-view Clustering via Prototype-based Imputationcited by 21
  30. 2023Part Aware Contrastive Learning for Self-Supervised Action Recognitioncited by 21
  31. 2021Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identificationcited by 18
  32. 2021Self-supervised Contrastive Attributed Graph Clusteringcited by 18
  33. 2022Label-invariant Augmentation for Semi-Supervised Graph Classificationcited by 18
  34. 2023DivClust: Controlling Diversity in Deep Clusteringcited by 18
  35. 2022Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognitioncited by 17
  36. 2022Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metriccited by 17
  37. 2023Contrastive Tuning: A Little Help to Make Masked Autoencoders Forgetcited by 15
  38. 2025I-Con: A Unifying Framework for Representation Learningcited by 15

50 most cited of 264 All 264 (JSON)