Procrustean Training for Imbalanced Deep Learning

TL;DR

This paper introduces a novel training strategy for imbalanced deep learning that balances class training progress, preventing under-fitting of minor classes and improving overall accuracy on benchmark datasets.

Contribution

The paper proposes a feature mixing method to equalize training across classes, addressing the under-fitting and over-fitting issues in imbalanced neural network training.

Findings

Achieves state-of-the-art accuracy on benchmark datasets.

Effectively mitigates under-fitting and over-fitting in imbalanced training.

Improves performance especially on step-imbalanced cases.

Abstract

Neural networks trained with class-imbalanced data are known to perform poorly on minor classes of scarce training data. Several recent works attribute this to over-fitting to minor classes. In this paper, we provide a novel explanation of this issue. We found that a neural network tends to first under-fit the minor classes by classifying most of their data into the major classes in early training epochs. To correct these wrong predictions, the neural network then must focus on pushing features of minor class data across the decision boundaries between major and minor classes, leading to much larger gradients for features of minor classes. We argue that such an under-fitting phase over-emphasizes the competition between major and minor classes, hinders the neural network from learning the discriminative knowledge that can be generalized to test data, and eventually results in over-fitting. To address this issue, we propose a novel learning strategy to equalize the training progress across classes. We mix features of the major class data with those of other data in a mini-batch, intentionally weakening their features to prevent a neural network from fitting them first. We show that this strategy can largely balance the training accuracy and feature gradients across classes, effectively mitigating the under-fitting then over-fitting problem for minor class data. On several benchmark datasets, our approach achieves the state-of-the-art accuracy, especially for the challenging step-imbalanced cases.