Foster Adaptivity and Balance in Learning with Noisy Labels

TL;DR

This paper introduces SED, a novel method for training deep neural networks with noisy labels that adaptively selects samples, balances classes, and employs label correction and regularization to improve generalization.

Contribution

The paper proposes a self-adaptive, class-balanced approach for handling noisy labels, combining sample selection, label correction, and regularization, which outperforms existing methods.

Findings

Effective in both synthetic and real-world datasets.

Improves generalization and robustness to label noise.

Outperforms state-of-the-art methods in experiments.

Abstract

Label noise is ubiquitous in real-world scenarios, posing a practical challenge to supervised models due to its effect in hurting the generalization performance of deep neural networks. Existing methods primarily employ the sample selection paradigm and usually rely on dataset-dependent prior knowledge (\eg, a pre-defined threshold) to cope with label noise, inevitably degrading the adaptivity. Moreover, existing methods tend to neglect the class balance in selecting samples, leading to biased model performance. To this end, we propose a simple yet effective approach named \textbf{SED} to deal with label noise in a \textbf{S}elf-adaptiv\textbf{E} and class-balance\textbf{D} manner. Specifically, we first design a novel sample selection strategy to empower self-adaptivity and class balance when identifying clean and noisy data. A mean-teacher model is then employed to correct labels of noisy samples. Subsequently, we propose a self-adaptive and class-balanced sample re-weighting mechanism to assign different weights to detected noisy samples. Finally, we additionally employ consistency regularization on selected clean samples to improve model generalization performance. Extensive experimental results on synthetic and real-world datasets demonstrate the effectiveness and superiority of our proposed method. The source code has been made available at https://github.com/NUST-Machine-Intelligence-Laboratory/SED.