571 citations · 1.2k across the 14 of their papers we have counts for
5 papers · 1 filter
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
Dan Hendrycks, Norman Mu, Ekin D. Cubuk +3
Modern deep neural networks can achieve high accuracy when the training distribution and test distribution are identically distributed, but this assumption is frequently violated i…
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
Raphael Gontijo Lopes, Dong Yin, Ben Poole +2
Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions. While architectural advances have…
MNIST-C: A Robustness Benchmark for Computer Vision
Norman Mu, Justin Gilmer
We introduce the MNIST-C dataset, a comprehensive suite of 15 corruptions applied to the MNIST test set, for benchmarking out-of-distribution robustness in computer vision. Through…
A Fourier Perspective on Model Robustness in Computer Vision
Dong Yin, Raphael Gontijo Lopes, Jonathon Shlens +2
Achieving robustness to distributional shift is a longstanding and challenging goal of computer vision. Data augmentation is a commonly used approach for improving robustness, howe…
Adversarial Examples Are a Natural Consequence of Test Error in Noise
Nic Ford, Justin Gilmer, Nicolas Carlini +1
Over the last few years, the phenomenon of adversarial examples --- maliciously constructed inputs that fool trained machine learning models --- has captured the attention of the r…