# Subclass-balancing Contrastive Learning for Long-tailed Recognition

arXiv: https://arxiv.org/abs/2306.15925 · HTML: https://mlsanity.com/paper/2306.15925/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 77 references that are in the map.
- First posted on arXiv 28 Jun 2023.

## Builds on (most cited first, 30 of 57)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (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)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Understanding the Behaviour of Contrastive Loss](https://mlsanity.com/paper/2012.09740/) (2020)
- [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://mlsanity.com/paper/1905.11001/) (2019)

## Built on by (most cited first, 26 of 26)

- [A Systematic Review on Long-Tailed Learning](https://mlsanity.com/paper/2408.00483/) (2024)
- [A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization](https://mlsanity.com/paper/2310.04752/) (2023)
- [Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentation](https://mlsanity.com/paper/2407.04911/) (2024)
- [Cluster-guided Contrastive Class-imbalanced Graph Classification](https://mlsanity.com/paper/2412.12984/) (2024)
- [Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Model](https://mlsanity.com/paper/2507.22615/) (2025)
- [Towards Long-Tailed Recognition for Graph Classification via Collaborative Experts](https://mlsanity.com/paper/2308.16609/) (2023)
- [A Tale of Two Classes: Adapting Supervised Contrastive Learning to Binary Imbalanced Datasets](https://mlsanity.com/paper/2503.17024/) (2025)
- [Curvature Learning for Generalization of Hyperbolic Neural Networks](https://mlsanity.com/paper/2508.17232/) (2025)
- [Long-Tail Learning with Rebalanced Contrastive Loss](https://mlsanity.com/paper/2312.01753/) (2023)
- [DiffuLT: How to Make Diffusion Model Useful for Long-tail Recognition](https://mlsanity.com/paper/2403.05170/) (2024)
- [Extracting Clean and Balanced Subset for Noisy Long-tailed Classification](https://mlsanity.com/paper/2404.06795/) (2024)
- [All-around Neural Collapse for Imbalanced Classification](https://mlsanity.com/paper/2408.07253/) (2024)
- [pNNCLR: Stochastic Pseudo Neighborhoods for Contrastive Learning based Unsupervised Representation Learning Problems](https://mlsanity.com/paper/2308.06983/) (2023)
- [SP2OT: Semantic-Regularized Progressive Partial Optimal Transport for Imbalanced Clustering](https://mlsanity.com/paper/2404.03446/) (2024)
- [Skin Lesion Phenotyping via Nested Multi-modal Contrastive Learning](https://mlsanity.com/paper/2505.23709/) (2025)
- [Boosting Adverse Weather Crowd Counting via Multi-queue Contrastive Learning](https://mlsanity.com/paper/2408.05956/) (2024)
- [Aligned Contrastive Loss for Long-Tailed Recognition](https://mlsanity.com/paper/2506.01071/) (2025)
- [Long-Tailed Recognition via Information-Preservable Two-Stage Learning](https://mlsanity.com/paper/2510.08836/) (2025)
- [Optimizing for ROC Curves on Class-Imbalanced Data by Training over a Family of Loss Functions](https://mlsanity.com/paper/2402.05400/) (2024)
- [Training Over a Distribution of Hyperparameters for Enhanced Performance and Adaptability on Imbalanced Classification](https://mlsanity.com/paper/2410.03588/) (2024)
- [Dataset Awareness is not Enough: Implementing Sample-level Tail Encouragement in Long-tailed Self-supervised Learning](https://mlsanity.com/paper/2410.22883/) (2024)
- [Sub-Clustering for Class Distance Recalculation in Long-Tailed Drug Classification](https://mlsanity.com/paper/2504.04647/) (2025)
- [Optimizing Class Distributions for Bias-Aware Multi-Class Learning](https://mlsanity.com/paper/2509.11588/) (2025)
- [Exploring "Many in Few" and "Few in Many" Properties in Long-Tailed, Highly-Imbalanced IC Defect Classification](https://mlsanity.com/paper/2510.19463/) (2025)
- [Flow Matching with Optimized Subclass Priors for Medical Image Augmentation](https://mlsanity.com/paper/2605.16469/) (2026)
- [OFBD: Object-Focused Background Debiasing for Long-Tailed Learning](https://mlsanity.com/paper/2609.37331/) (2026)

## Abstract (arXiv)

Long-tailed recognition with imbalanced class distribution naturally emerges in practical machine learning applications. Existing methods such as data reweighing, resampling, and supervised contrastive learning enforce the class balance with a price of introducing imbalance between instances of head class and tail class, which may ignore the underlying rich semantic substructures of the former and exaggerate the biases in the latter. We overcome these drawbacks by a novel ``subclass-balancing contrastive learning (SBCL)'' approach that clusters each head class into multiple subclasses of similar sizes as the tail classes and enforce representations to capture the two-layer class hierarchy between the original classes and their subclasses. Since the clustering is conducted in the representation space and updated during the course of training, the subclass labels preserve the semantic substructures of head classes. Meanwhile, it does not overemphasize tail class samples, so each individual instance contribute to the representation learning equally. Hence, our method achieves both the instance- and subclass-balance, while the original class labels are also learned through contrastive learning among subclasses from different classes. We evaluate SBCL over a list of long-tailed benchmark datasets and it achieves the state-of-the-art performance. In addition, we present extensive analyses and ablation studies of SBCL to verify its advantages.