mlsanityData to 7 Oct 2026

Twin Contrastive Learning for Online Clustering

arXiv 2210.11680 ↗First posted 21 Oct 2022cs.LGcited by 60

Not on the map. Why?

Abstract (arXiv)

This paper proposes to perform online clustering by conducting twin contrastive learning (TCL) at the instance and cluster level. Specifically, we find that when the data is projected into a feature space with a dimensionality of the target cluster number, the rows and columns of its feature matrix correspond to the instance and cluster representation, respectively. Based on the observation, for a given dataset, the proposed TCL first constructs positive and negative pairs through data augmentations. Thereafter, in the row and column space of the feature matrix, instance- and cluster-level contrastive learning are respectively conducted by pulling together positive pairs while pushing apart the negatives. To alleviate the influence of intrinsic false-negative pairs and rectify cluster assignments, we adopt a confidence-based criterion to select pseudo-labels for boosting both the instance- and cluster-level contrastive learning. As a result, the clustering performance is further improved. Besides the elegant idea of twin contrastive learning, another advantage of TCL is that it could independently predict the cluster assignment for each instance, thus effortlessly fitting online scenarios. Extensive experiments on six widely-used image and text benchmarks demonstrate the effectiveness of TCL. The code will be released on GitHub.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). Builds on 45 of its 94 references that are in the map. First posted on arXiv 21 Oct 2022.

Builds on

45 of 94 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  8. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  9. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  10. 2020Supervised Contrastive Learningcited by 2,803
  11. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  12. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
33 more
  1. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  2. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  3. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  4. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  5. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  6. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
  7. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
  8. 2014Distributed Representations of Sentences and Documentscited by 677
  9. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 636
  10. 2019Self-labelling via simultaneous clustering and representation learningcited by 525
  11. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 454
  12. 2020SCAN: Learning to Classify Images without Labelscited by 351
  13. 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 324
  14. 2015Skip-Thought Vectorscited by 321
  15. 2016Joint Unsupervised Learning of Deep Representations and Image Clusterscited by 205
  16. 2019NLNL: Negative Learning for Noisy Labelscited by 151
  17. 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
  18. 2017Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimizationcited by 113
  19. 2021SPICE: Semantic Pseudo-labeling for Image Clusteringcited by 104
  20. 2021Contrastive Learning with Stronger Augmentationscited by 100
  21. 2020AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversariescited by 90
  22. 2021Supporting Clustering with Contrastive Learningcited by 90
  23. 2019Deep Comprehensive Correlation Mining for Image Clusteringcited by 80
  24. 2020Unsupervised Feature Learning by Cross-Level Instance-Group Discriminationcited by 51
  25. 2020Improving Unsupervised Image Clustering With Robust Learningcited by 51
  26. 2021Revisiting Contrastive Methods for Unsupervised Learning of Visual Representationscited by 48
  27. 2017Self-Taught Convolutional Neural Networks for Short Text Clusteringcited by 34
  28. 2019Deep Discriminative Clustering Analysiscited by 28
  29. 2020Deep Robust Clustering by Contrastive Learningcited by 25
  30. 2018XAI Beyond Classification: Interpretable Neural Clusteringcited by 24
  31. 2021Structure-Aware Face Clustering on a Large-Scale Graph with bf107 Nodescited by 21
  32. 2020Enhancement of Short Text Clustering by Iterative Classificationcited by 16
  33. 2021Doubly Contrastive Deep Clusteringcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 19; 2024: 12; 2025: 21; 2026: 7.

60 papers.

Sort:

By area:

  1. 2023Deep Multiview Clustering by Contrasting Cluster Assignmentscited by 33
  2. 2022Graph Matching with Bi-level Noisy Correspondencecited by 30
  3. 2023Image Clustering Conditioned on Text Criteriacited by 26
  4. 2023Novel Class Discovery: an Introduction and Key Conceptscited by 24
  5. 2023Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Modelscited by 22
  6. 2023Incomplete Multi-view Clustering via Prototype-based Imputationcited by 21
  7. 2023Learning from History: Task-agnostic Model Contrastive Learning for Image Restorationcited by 11
  8. 2023Tree Variational Autoencoderscited by 10
  9. 2023Contextually Affinitive Neighborhood Refinery for Deep Clusteringcited by 10
  10. 2023A Clustering Framework for Unsupervised and Semi-supervised New Intent Discoverycited by 9
  11. 2024A Survey on Deep Clustering: From the Prior Perspectivecited by 9
  12. 2025On the Provable Importance of Gradients for Language-Assisted Image Clusteringcited by 8
38 more
  1. 2025Imputation-free and Alignment-free: Incomplete Multi-view Clustering Driven by Consensus Semantic Learningcited by 7
  2. 2025Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detectioncited by 6
  3. 2024Multi-level Cross-modal Alignment for Image Clusteringcited by 5
  4. 2025Hierarchical Semantic Alignment for Image Clusteringcited by 5
  5. 2023Distortion-Disentangled Contrastive Learningcited by 4
  6. 2024Personalized Clustering via Targeted Representation Learningcited by 4
  7. 2025Deep Incomplete Multi-view Clustering with Distribution Dual-Consistency Recovery Guidancecited by 4
  8. 2025Fuzzy Cluster-Aware Contrastive Clustering for Time Seriescited by 4
  9. 2023Differentiable Random Partition Modelscited by 3
  10. 2023Hate Speech Detection via Dual Contrastive Learningcited by 3
  11. 2024Towards Calibrated Deep Clustering Networkcited by 3
  12. 2024Deep Clustering with Self-Supervision using Pairwise Similaritiescited by 3
  13. 2024From Logits to Hierarchies: Hierarchical Clustering made Simplecited by 3
  14. 2025CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectorscited by 3
  15. 2025Wasserstein-Aligned Hyperbolic Multi-View Clusteringcited by 3
  16. 2023Semantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination Methodscited by 2
  17. 2024MMCL: Correcting Content Query Distributions for Improved Anti-Overlapping X-Ray Object Detectioncited by 2
  18. 2024Deep Online Probability Aggregation Clusteringcited by 2
  19. 2025PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clusteringcited by 2
  20. 2025You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clusteringcited by 2
  21. 2026Delving into Spectral Clustering with Vision-Language Representationscited by 2
  22. 2023ScoreCL: Augmentation-Adaptive Contrastive Learning via Score-Matching Functioncited by 1
  23. 2023CAST: Cluster-Aware Self-Training for Tabular Data via Reliable Confidencecited by 1
  24. 2023Cross-View Graph Consistency Learning for Invariant Graph Representationscited by 1
  25. 2025Gene-DML: Dual-Pathway Multi-Level Discrimination for Gene Expression Prediction from Histopathology Imagescited by 1
  26. 2025Self-Enhanced Image Clustering with Cross-Modal Semantic Consistencycited by 1
  27. 2026Deep Temporal Graph Clustering: A Comprehensive Benchmark and Datasetscited by 1
  28. 2026CLUBench: A Clustering Benchmarkcited by 1
  29. 2023Learning Structure Aware Deep Spectral Embeddingcited by 0
  30. 2023Grid Jigsaw Representation with CLIP: A New Perspective on Image Clusteringcited by 0
  31. 2023Probing clustering in neural network representationscited by 0
  32. 2024Learning Representations for Clustering via Partial Information Discrimination and Cross-Level Interactioncited by 0
  33. 2024CGRclust: Chaos Game Representation for Twin Contrastive Clustering of Unlabelled DNA Sequencescited by 0
  34. 2024Clustering-friendly Representation Learning for Enhancing Salient Featurescited by 0
  35. 2024Active-Passive Federated Learning for Vertically Partitioned Multi-view Datacited by 0
  36. 2025Deep Clustering via Gradual Community Detectioncited by 0
  37. 2025Graph Probability Aggregation Clusteringcited by 0
  38. 2025Infinite hierarchical contrastive clustering for personal digital envirotypingcited by 0

50 most cited of 60 All 60 (JSON)