Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selection

TL;DR

This paper introduces a novel approach to training deep models on imbalanced datasets with noisy labels by preventing bias in sample selection and employing label correction and regularization techniques.

Contribution

It proposes Class-Balance-based sample Selection (CBS), Confidence-based Sample Augmentation (CSA), and label correction with the Average Confidence Margin (ACM) to improve learning under noisy, imbalanced conditions.

Findings

Outperforms existing methods on synthetic and real-world datasets.

Effectively handles class imbalance and label noise.

Improves model robustness and accuracy.

Abstract

Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples as clean ones and discard high-loss ones to alleviate the negative impact of noisy labels. However, real-world datasets contain not only noisy labels but also class imbalance. The imbalance issue is prone to causing failure in the loss-based sample selection since the under-learning of tail classes also leans to produce high losses. To this end, we propose a simple yet effective method to address noisy labels in imbalanced datasets. Specifically, we propose Class-Balance-based sample Selection (CBS) to prevent the tail class samples from being neglected during training. We propose Confidence-based Sample Augmentation (CSA) for the chosen clean samples to enhance their reliability in the training process. To exploit selected noisy samples, we resort to prediction history to rectify labels of noisy samples. Moreover, we introduce the Average Confidence Margin (ACM) metric to measure the quality of corrected labels by leveraging the model's evolving training dynamics, thereby ensuring that low-quality corrected noisy samples are appropriately masked out. Lastly, consistency regularization is imposed on filtered label-corrected noisy samples to boost model performance. Comprehensive experimental results on synthetic and real-world datasets demonstrate the effectiveness and superiority of our proposed method, especially in imbalanced scenarios. Comprehensive experimental results on synthetic and real-world datasets demonstrate the effectiveness and superiority of our proposed method, especially in imbalanced scenarios.