Simplifying Neural Network Training Under Class Imbalance
This provides a simpler, effective solution for practitioners dealing with imbalanced data, though it is incremental as it builds on existing tuning practices.
The paper tackles the problem of training neural networks on class-imbalanced datasets by showing that tuning standard pipeline components like batch size and data augmentation achieves state-of-the-art performance without specialized methods.
Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models. The majority of research on training neural networks under class imbalance has focused on specialized loss functions, sampling techniques, or two-stage training procedures. Notably, we demonstrate that simply tuning existing components of standard deep learning pipelines, such as the batch size, data augmentation, optimizer, and label smoothing, can achieve state-of-the-art performance without any such specialized class imbalance methods. We also provide key prescriptions and considerations for training under class imbalance, and an understanding of why imbalance methods succeed or fail.