RandoMix: A mixed sample data augmentation method with multiple mixed modes
This is an incremental improvement in data augmentation methods for machine learning practitioners seeking better model performance and robustness.
The paper tackled the problem of improving model robustness and diversity in machine learning by introducing RandoMix, a mixed-sample data augmentation method that outperformed existing techniques like Mixup and CutMix on datasets including CIFAR-10/100 and ImageNet, enhancing robustness against adversarial noise, natural noise, and sample occlusion.
Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains. In this study, we introduce a novel mixed-sample data augmentation method called RandoMix. RandoMix is specifically designed to simultaneously address robustness and diversity challenges. It leverages a combination of linear and mask-mixed modes, introducing flexibility in candidate selection and weight adjustments. We evaluate the effectiveness of RandoMix on diverse datasets, including CIFAR-10/100, Tiny-ImageNet, ImageNet, and Google Speech Commands. Our results demonstrate its superior performance compared to existing techniques such as Mixup, CutMix, Fmix, and ResizeMix. Notably, RandoMix excels in enhancing model robustness against adversarial noise, natural noise, and sample occlusion. The comprehensive experimental results and insights into parameter tuning underscore the potential of RandoMix as a versatile and effective data augmentation method. Moreover, it seamlessly integrates into the training pipeline.