Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
Paper summary Lopes et al. propose patch-based Gaussian data augmentation to improve accuracy and robustness against common corruptions. Their approach is intended to be an interpolation between Gaussian noise data augmentation and CutOut. During training, random patches on images are selected and random Gaussian noise is added to these patches. With increasing noise level (i.e., its standard deviation) this results in CutOut; with increasing patch size, this results in regular Gaussian noise data augmentation. On ImageNet-C and Cifar-C, the authors show that this approach improves robustness against common corruptions while also improving accuracy slightly. Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).
arxiv.org
scholar.google.com
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
Lopes, Raphael Gontijo and Yin, Dong and Poole, Ben and Gilmer, Justin and Cubuk, Ekin D.
arXiv e-Print archive - 2019 via Local Bibsonomy
Keywords: dblp


[link]
Summary by David Stutz 3 weeks ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and