DropMix: Reducing Class Dependency in Mixed Sample Data Augmentation

Mixed sample data augmentation (MSDA) is a widely used technique that has been found to improve performance in a variety of tasks. However, in this paper, we show that the effects of MSDA are class-dependent, with some classes seeing an improvement in performance while others experience a decline. To reduce class dependency, we propose the DropMix method, which excludes a specific percentage of data from the MSDA computation. By training on a combination of MSDA and non-MSDA data, the proposed method not only improves the performance of classes that were previously degraded by MSDA, but also increases overall average accuracy, as shown in experiments on two datasets (CIFAR-100 and ImageNet) using three MSDA methods (Mixup, CutMix and PuzzleMix).