Phased Progressive Learning with Coupling-Regulation-Imbalance Loss for Imbalanced Data Classification
This work addresses dataset bias and domain shift in imbalanced data classification, which is a common issue in machine learning applications, though it appears incremental as it builds on existing two-stage approaches.
The paper tackles the problem of poor performance of deep convolutional neural networks on imbalanced datasets by introducing a phased progressive learning schedule and a coupling-regulation-imbalance loss function, achieving satisfactory results on benchmark datasets like Imbalanced CIFAR10, CIFAR100, ImageNet-LT, and iNaturalist 2018.
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.