AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

Abstract

Modern deep neural networks can achieve high accuracy when the training distribution and test distribution are identically distributed, but this assumption is frequently violated in practice. When the train and test distributions are mismatched, accuracy can plummet. Currently there are few techniques that improve robustness to unforeseen data shifts encountered during deployment. In this work, we propose a technique to improve the robustness and uncertainty estimates of image classifiers. We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions. AugMix significantly improves robustness and uncertainty measures on challenging image classification benchmarks, closing the gap between previous methods and the best possible performance in some cases by more than half.

Code available at https://github.com/google-research/augmix

References in corpus (7)

• Improved Regularization of Convolutional Neural Networks with Cutout
• On Calibration of Modern Neural Networks
• Random Erasing Data Augmentation
• Deep Anomaly Detection with Outlier Exposure
• Making Convolutional Networks Shift-Invariant Again
• Learning with Pseudo-Ensembles
• Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation

Cited by in corpus (2)

• Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition
• Extending Label Smoothing Regularization with Self-Knowledge Distillation