Reviews: On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks

The paper studies a newly proposed data augmentation method Mixup from a calibration perspective. The authors empirically show that models trained with Mixup are significantly better calibrated, in terms of the correlation between the predicted softmax score and the actual likelihood of a correct prediction, when compared to models trained without Mixup. The empirical studies of the paper also show that mixup-trained models are less prone to over-confident prediction on out-of-distribution data, and the label smoothing in Mixup is critical for achieving the desirable calibration outcomes. The paper is well written and easy to follow. The new view of looking into the newly proposed data augmentation method Mixup is interesting and could be practically useful for application where uncertainty is a significant concern.