Combating Noisy Labels in Long-Tailed Image Classification

TL;DR

This paper introduces a novel learning paradigm for long-tailed image classification with noisy labels, effectively distinguishing noisy from clean samples and reducing bias towards head classes, outperforming existing methods.

Contribution

It proposes a new approach combining inference matching, leave-noise-out regularization, and online prior distribution penalties for robust long-tailed classification with noisy labels.

Findings

Outperforms state-of-the-art long-tail classification methods with noisy labels.

Effectively screens out noisy samples in tail classes.

Reduces bias towards head classes in imbalanced datasets.

Abstract

Most existing methods that cope with noisy labels usually assume that the class distributions are well balanced, which has insufficient capacity to deal with the practical scenarios where training samples have imbalanced distributions. To this end, this paper makes an early effort to tackle the image classification task with both long-tailed distribution and label noise. Existing noise-robust learning methods cannot work in this scenario as it is challenging to differentiate noisy samples from clean samples of tail classes. To deal with this problem, we propose a new learning paradigm based on matching between inferences on weak and strong data augmentations to screen out noisy samples and introduce a leave-noise-out regularization to eliminate the effect of the recognized noisy samples. Furthermore, we incorporate a novel prediction penalty based on online prior distribution to avoid bias towards head classes. This mechanism has superiority in capturing the class fitting degree in realtime compared to the existing long-tail classification methods. Exhaustive experiments demonstrate that the proposed method outperforms state-of-the-art algorithms that address the distribution imbalance problem in long-tailed classification under noisy labels.