Balanced Contrastive Learning for Long-Tailed Visual Recognition
Preprint
Abstract
Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data while most minority categories contain a limited number of samples. Classification models minimizing cross-entropy struggle to represent and classify the tail classes. Although the problem of learning unbiased classifiers has been well studied, methods for representing imbalanced data are under-explored. In this paper, we focus on representation learning for imbalanced data. Recently, supervised contrastive learning has shown promising performance on balanced data recently. However, through our theoretical analysis, we find that for long-tailed data, it fails to form a regular simplex which is an ideal geometric configuration for representation learning. To correct the optimization behavior of SCL and further improve the performance of long-tailed visual recognition, we propose a novel loss for balanced contrastive learning (BCL). Compared with SCL, we have two improvements in BCL: class-averaging, which balances the gradient contribution of negative classes; class-complement, which allows all classes to appear in every mini-batch. The proposed balanced contrastive learning (BCL) method satisfies the condition of forming a regular simplex and assists the optimization of cross-entropy. Equipped with BCL, the proposed two-branch framework can obtain a stronger feature representation and achieve competitive performance on long-tailed benchmark datasets such as CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, and iNaturalist2018. Our code is available at https://github.com/FlamieZhu/BCL .Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Targeted Supervised Contrastive Learning for Long-Tailed Recognition2022
- ResLT: Residual Learning for Long-tailed RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- Cross-Domain Contrastive Learning for Unsupervised Domain AdaptationIEEE Transactions on Multimedia, 2022
- Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced trainingProceedings of the National Academy of Sciences, 2021
- A Study of Multi-Task and Region-Wise Deep Learning for Food Ingredient RecognitionIEEE Transactions on Image Processing, 2020
- A systematic study of the class imbalance problem in convolutional neural networksNeural Networks, 2018