Balanced Contrastive Learning for Long-Tailed Visual Recognition
Authors:
Top Cited Papers
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6898-6907
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 crossentropy 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: classaveraging, 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.Keywords
All Related Versions
Funding Information
- NSFC (62072116)
This publication has 28 references indexed in Scilit:
- Mixed-dish Recognition with Contextual Relation Networks2019
- AutoAugment: Learning Augmentation Strategies From Data2019
- Class-Balanced Loss Based on Effective Number of Samples2019
- A systematic study of the class imbalance problem in convolutional neural networksNeural Networks, 2018
- Dynamic Sampling in Convolutional Neural Networks for Imbalanced Data Classification2018
- Focal Loss for Dense Object Detection2017
- Aggregated Residual Transformations for Deep Neural Networks2017
- Deep Residual Learning for Image Recognition2016
- Learning Deep Representation for Imbalanced Classification2016
- ImageNet: A large-scale hierarchical image database2009