In this paper we propose a new augmentation technique, called patch augmentation, that, in our experiments, improves model accuracy and makes networks more robust to adversarial attacks. In brief, this data-independent approach creates new image data based on image/label pairs, where a patch from one of the two images in the pair is superimposed on to the other image, creating a new augmented sample. The new image's label is a linear combination of the image pair's corresponding labels. Initial experiments show a several percentage point increase in accuracy on CIFAR-10, from a baseline of approximately 81% to 89%. CIFAR-100 sees larger improvements still, from a baseline of 52% to 68% accuracy. Networks trained using patch augmentation are also more robust to adversarial attacks, which we demonstrate using the Fast Gradient Sign Method.
@article{arxiv.1911.07922,
title = {Patch augmentation: Towards efficient decision boundaries for neural networks},
author = {Marcus D. Bloice and Peter M. Roth and Andreas Holzinger},
journal= {arXiv preprint arXiv:1911.07922},
year = {2019}
}
Comments
Version 2: updated author list, reduced abstract length, plots consolidated as sub-plots