Neural collapse inspired attraction-repulsion-balanced loss for imbalanced learning

Class imbalance distribution widely exists in real-world engineering. However, the mainstream optimiza-tion algorithms that seek to minimize error will trap the deep learning model in sub-optimums when fac-ing extreme class imbalance. It seriously harms the classification precision, especially in the minor classes. The essential reason is that the gradients of the classifier weights are imbalanced among the com-ponents 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 large-scale classifica-tion 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.(c) 2023 Elsevier B.V. All rights reserved.