# Twin Contrastive Learning for Online Clustering

arXiv: https://arxiv.org/abs/2210.11680 · HTML: https://mlsanity.com/paper/2210.11680/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 94 references that are in the map.
- First posted on arXiv 21 Oct 2022.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [SCAN: Learning to Classify Images without Labels](https://mlsanity.com/paper/2005.12320/) (2020)
- [With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2104.14548/) (2021)
- [Skip-Thought Vectors](https://mlsanity.com/paper/1506.06726/) (2015)
- [Joint Unsupervised Learning of Deep Representations and Image Clusters](https://mlsanity.com/paper/1604.03628/) (2016)
- [NLNL: Negative Learning for Noisy Labels](https://mlsanity.com/paper/1908.07387/) (2019)
- [Learning Discrete Representations via Information Maximizing Self-Augmented Training](https://mlsanity.com/paper/1702.08720/) (2017)
- [Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization](https://mlsanity.com/paper/1704.06327/) (2017)

## Built on by (most cited first, 30 of 60)

- [Deep Multiview Clustering by Contrasting Cluster Assignments](https://mlsanity.com/paper/2304.10769/) (2023)
- [Graph Matching with Bi-level Noisy Correspondence](https://mlsanity.com/paper/2212.04085/) (2022)
- [Image Clustering Conditioned on Text Criteria](https://mlsanity.com/paper/2310.18297/) (2023)
- [Novel Class Discovery: an Introduction and Key Concepts](https://mlsanity.com/paper/2302.12028/) (2023)
- [Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models](https://mlsanity.com/paper/2306.05272/) (2023)
- [Incomplete Multi-view Clustering via Prototype-based Imputation](https://mlsanity.com/paper/2301.11045/) (2023)
- [Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration](https://mlsanity.com/paper/2309.06023/) (2023)
- [Tree Variational Autoencoders](https://mlsanity.com/paper/2306.08984/) (2023)
- [Contextually Affinitive Neighborhood Refinery for Deep Clustering](https://mlsanity.com/paper/2312.07806/) (2023)
- [A Clustering Framework for Unsupervised and Semi-supervised New Intent Discovery](https://mlsanity.com/paper/2304.07699/) (2023)
- [A Survey on Deep Clustering: From the Prior Perspective](https://mlsanity.com/paper/2406.19602/) (2024)
- [On the Provable Importance of Gradients for Language-Assisted Image Clustering](https://mlsanity.com/paper/2510.16335/) (2025)
- [Imputation-free and Alignment-free: Incomplete Multi-view Clustering Driven by Consensus Semantic Learning](https://mlsanity.com/paper/2505.11182/) (2025)
- [Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection](https://mlsanity.com/paper/2504.07060/) (2025)
- [Multi-level Cross-modal Alignment for Image Clustering](https://mlsanity.com/paper/2401.11740/) (2024)
- [Hierarchical Semantic Alignment for Image Clustering](https://mlsanity.com/paper/2512.00904/) (2025)
- [Distortion-Disentangled Contrastive Learning](https://mlsanity.com/paper/2303.05066/) (2023)
- [Towards Calibrated Deep Clustering Network](https://mlsanity.com/paper/2403.02998/) (2024)
- [Personalized Clustering via Targeted Representation Learning](https://mlsanity.com/paper/2412.13690/) (2024)
- [Deep Incomplete Multi-view Clustering with Distribution Dual-Consistency Recovery Guidance](https://mlsanity.com/paper/2503.11017/) (2025)
- [Fuzzy Cluster-Aware Contrastive Clustering for Time Series](https://mlsanity.com/paper/2503.22211/) (2025)
- [Differentiable Random Partition Models](https://mlsanity.com/paper/2305.16841/) (2023)
- [Hate Speech Detection via Dual Contrastive Learning](https://mlsanity.com/paper/2307.05578/) (2023)
- [Deep Clustering with Self-Supervision using Pairwise Similarities](https://mlsanity.com/paper/2405.03590/) (2024)
- [From Logits to Hierarchies: Hierarchical Clustering made Simple](https://mlsanity.com/paper/2410.07858/) (2024)
- [CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectors](https://mlsanity.com/paper/2501.16665/) (2025)
- [Wasserstein-Aligned Hyperbolic Multi-View Clustering](https://mlsanity.com/paper/2512.09402/) (2025)
- [Semantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination Methods](https://mlsanity.com/paper/2306.16122/) (2023)
- [MMCL: Correcting Content Query Distributions for Improved Anti-Overlapping X-Ray Object Detection](https://mlsanity.com/paper/2406.03176/) (2024)
- [Deep Online Probability Aggregation Clustering](https://mlsanity.com/paper/2407.05246/) (2024)

## 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.