SMCL: Saliency Masked Contrastive Learning for Long-tailed Recognition

TL;DR

This paper introduces Saliency Masked Contrastive Learning (SMCL), a novel approach that uses saliency detection and contrastive learning to address class imbalance in long-tailed datasets, improving model generalization.

Contribution

The paper proposes a new method combining saliency masking with contrastive learning to reduce background bias in long-tailed recognition tasks.

Findings

Achieves state-of-the-art performance on benchmark long-tailed datasets.

Effectively reduces background feature bias in imbalanced data.

Improves model generalization to minority classes.

Abstract

Real-world data often follow a long-tailed distribution with a high imbalance in the number of samples between classes. The problem with training from imbalanced data is that some background features, common to all classes, can be unobserved in classes with scarce samples. As a result, this background correlates to biased predictions into ``major" classes. In this paper, we propose saliency masked contrastive learning, a new method that uses saliency masking and contrastive learning to mitigate the problem and improve the generalizability of a model. Our key idea is to mask the important part of an image using saliency detection and use contrastive learning to move the masked image towards minor classes in the feature space, so that background features present in the masked image are no longer correlated with the original class. Experiment results show that our method achieves state-of-the-art level performance on benchmark long-tailed datasets.