Corpus ID: 174802797

Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation

@article{Lopes2019ImprovingRW,
  title={Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation},
  author={Raphael Gontijo Lopes and Dong Yin and Ben Poole and J. Gilmer and E. Cubuk},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.02611}
}

Raphael Gontijo Lopes, Dong Yin, +2 authors E. Cubuk

Published 2019

Computer Science, Mathematics

ArXiv

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 led to improved accuracy, building robust models remains challenging. Prior work has argued that there is an inherent trade-off between robustness and accuracy, which is exemplified by standard data augment techniques such as Cutout, which improves clean accuracy but not robustness, and additive Gaussian noise, which… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed