What are effective labels for augmented data? Improving robustness with AutoLabel

Yao Qin, Xuezhi Wang, Balaji Lakshminarayanan, Ed Chi, Alex Beutel

Keywords: data augmentation, image classification, calibration, distributional shifts, adversarial robustness

Abstract: A wide breadth of research has devised data augmentation approaches that can improve both accuracy and generalization performance for neural networks. However, augmented data can end up being far from the clean data and what is the appropriate label is less clear. Despite this, most existing work simply reuses the original label from the clean data, and the choice of label accompanying the augmented data is relatively less explored. In this paper, we propose AutoLabel to automatically learn the labels for augmented data, based on the distance between the clean distribution and augmented distribution. AutoLabel is built on label smoothing and is guided by the calibration-performance over a hold-out validation set. We show that AutoLabel is a generic framework that can be easily applied to existing data augmentation methods, including AugMix, mixup, and adversarial training. Experiments on CIFAR-10, CIFAR-100 and ImageNet show that AutoLabel can improve models' accuracy and calibration performance, especially under distributional shift. Additionally, we demonstrate that AutoLabel can help adversarial training by bridging the gap between clean accuracy and adversarial robustness.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=F4LReCVvn