Phased Progressive Learning with Coupling-Regulation-Imbalance Loss for Imbalanced Data Classification

TL;DR

This paper introduces a phased progressive learning schedule and a novel coupling-regulation-imbalance loss function to improve deep neural network performance on imbalanced datasets, effectively addressing quantity imbalance and classification difficulty.

Contribution

It proposes a new training schedule and a combined loss function that together enhance classification accuracy on highly imbalanced datasets, with demonstrated effectiveness on multiple benchmarks.

Findings

Improved accuracy on Imbalanced CIFAR10 and CIFAR100

Effective handling of outliers and class imbalance

Generalizable approach to various imbalanced datasets

Abstract

Deep convolutional neural networks often perform poorly when faced with datasets that suffer from quantity imbalances and classification difficulties. Despite advances in the field, existing two-stage approaches still exhibit dataset bias or domain shift. To counter this, a phased progressive learning schedule has been proposed that gradually shifts the emphasis from representation learning to training the upper classifier. This approach is particularly beneficial for datasets with larger imbalances or fewer samples. Another new method a coupling-regulation-imbalance loss function is proposed, which combines three parts: a correction term, Focal loss, and LDAM loss. This loss is effective in addressing quantity imbalances and outliers, while regulating the focus of attention on samples with varying classification difficulties. These approaches have yielded satisfactory results on several benchmark datasets, including Imbalanced CIFAR10, Imbalanced CIFAR100, ImageNet-LT, and iNaturalist 2018, and can be easily generalized to other imbalanced classification models.