Co-learning: Learning from Noisy Labels with Self-supervision

TL;DR

This paper introduces Co-learning, a method combining supervised and self-supervised learning to effectively handle noisy labels, improving generalization by regularizing shared features and maximizing agreement between views.

Contribution

The paper proposes a novel co-learning framework that integrates supervised and self-supervised learning with shared feature constraints to combat noisy labels.

Findings

Co-learning outperforms state-of-the-art methods on benchmark datasets.

The method effectively regularizes models against noisy labels.

Experimental results demonstrate improved generalization.

Abstract

Noisy labels, resulting from mistakes in manual labeling or webly data collecting for supervised learning, can cause neural networks to overfit the misleading information and degrade the generalization performance. Self-supervised learning works in the absence of labels and thus eliminates the negative impact of noisy labels. Motivated by co-training with both supervised learning view and self-supervised learning view, we propose a simple yet effective method called Co-learning for learning with noisy labels. Co-learning performs supervised learning and self-supervised learning in a cooperative way. The constraints of intrinsic similarity with the self-supervised module and the structural similarity with the noisily-supervised module are imposed on a shared common feature encoder to regularize the network to maximize the agreement between the two constraints. Co-learning is compared with peer methods on corrupted data from benchmark datasets fairly, and extensive results are provided which demonstrate that Co-learning is superior to many state-of-the-art approaches.