Robust Long-Tailed Learning under Label Noise

TL;DR

This paper addresses the challenge of long-tailed learning with label noise, proposing a robust framework that detects noise and improves generalization, outperforming existing methods like DivideMix.

Contribution

It introduces a new prototypical noise detection method and a robust framework,~\algo, that effectively handles label noise in long-tailed distributions, enhancing model performance.

Findings

Outperforms DivideMix by 3% in test accuracy

Effective noise detection in long-tailed scenarios

Leverages semi-supervised learning for better generalization

Abstract

Long-tailed learning has attracted much attention recently, with the goal of improving generalisation for tail classes. Most existing works use supervised learning without considering the prevailing noise in the training dataset. To move long-tailed learning towards more realistic scenarios, this work investigates the label noise problem under long-tailed label distribution. We first observe the negative impact of noisy labels on the performance of existing methods, revealing the intrinsic challenges of this problem. As the most commonly used approach to cope with noisy labels in previous literature, we then find that the small-loss trick fails under long-tailed label distribution. The reason is that deep neural networks cannot distinguish correctly-labeled and mislabeled examples on tail classes. To overcome this limitation, we establish a new prototypical noise detection method by designing a distance-based metric that is resistant to label noise. Based on the above findings, we propose a robust framework,~\algo, that realizes noise detection for long-tailed learning, followed by soft pseudo-labeling via both label smoothing and diverse label guessing. Moreover, our framework can naturally leverage semi-supervised learning algorithms to further improve the generalisation. Extensive experiments on benchmark and real-world datasets demonstrate the superiority of our methods over existing baselines. In particular, our method outperforms DivideMix by 3\% in test accuracy. Source code will be released soon.