Selective-Supervised Contrastive Learning with Noisy Labels

TL;DR

This paper introduces Selective-Supervised Contrastive Learning (Sel-CL), a method that improves representation learning with noisy labels by selecting confident pairs, achieving state-of-the-art robustness without prior noise rate knowledge.

Contribution

Sel-CL extends supervised contrastive learning by effectively selecting confident pairs, enhancing robustness against noisy labels without needing noise rate information.

Findings

Sel-CL outperforms existing methods on multiple noisy datasets.

The method effectively identifies confident pairs without prior noise rate knowledge.

Sel-CL achieves state-of-the-art robustness in noisy label scenarios.

Abstract

Deep networks have strong capacities of embedding data into latent representations and finishing following tasks. However, the capacities largely come from high-quality annotated labels, which are expensive to collect. Noisy labels are more affordable, but result in corrupted representations, leading to poor generalization performance. To learn robust representations and handle noisy labels, we propose selective-supervised contrastive learning (Sel-CL) in this paper. Specifically, Sel-CL extend supervised contrastive learning (Sup-CL), which is powerful in representation learning, but is degraded when there are noisy labels. Sel-CL tackles the direct cause of the problem of Sup-CL. That is, as Sup-CL works in a \textit{pair-wise} manner, noisy pairs built by noisy labels mislead representation learning. To alleviate the issue, we select confident pairs out of noisy ones for Sup-CL without knowing noise rates. In the selection process, by measuring the agreement between learned representations and given labels, we first identify confident examples that are exploited to build confident pairs. Then, the representation similarity distribution in the built confident pairs is exploited to identify more confident pairs out of noisy pairs. All obtained confident pairs are finally used for Sup-CL to enhance representations. Experiments on multiple noisy datasets demonstrate the robustness of the learned representations by our method, following the state-of-the-art performance. Source codes are available at https://github.com/ShikunLi/Sel-CL