Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning

Abstract

Class imbalance distribution widely exists in real-world engineering. However, the mainstream optimization algorithms that seek to minimize error will trap the deep learning model in sub-optimums when facing extreme class imbalance. It seriously harms the classification precision, especially on the minor classes. The essential reason is that the gradients of the classifier weights are imbalanced among the components from different classes. In this paper, we propose Attraction-Repulsion-Balanced Loss (ARB-Loss) to balance the different components of the gradients. We perform experiments on the large-scale classification and segmentation datasets and our ARB-Loss can achieve state-of-the-art performance via only one-stage training instead of 2-stage learning like nowadays SOTA works.

25 pages, 5 figures, accepted by Neurocomputing

References in corpus (4)

• Prevalence of Neural Collapse during the terminal phase of deep learning training
• Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training
• Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path
• An Unconstrained Layer-Peeled Perspective on Neural Collapse

Cited by in corpus (1)

• Evaluating the Fairness of Neural Collapse in Medical Image Classification