Image Synthesis with a Single (Robust) Classifier
Authors
Authors
- Shibani Santurkar
- Andrew Ilyas
- Dimitris Tsipras
- Logan Engstrom
- Brandon Tran
- Aleksander Madry
Authors
- Shibani Santurkar
- Andrew Ilyas
- Dimitris Tsipras
- Logan Engstrom
- Brandon Tran
- Aleksander Madry
Published on
12/14/2019
Categories
We show that the basic classification framework alone can be used to tackle some of the most challenging tasks in image synthesis. In contrast to other state-of-theart approaches, the toolkit we develop is rather minimal: it uses a single, off-theshelf classifier for all these tasks. The crux of our approach is that we train this classifier to be adversarially robust. It turns out that adversarial robustness is precisely what we need to directly manipulate salient features of the input. Overall, our findings demonstrate the utility of robustness in the broader machine learning context.
This work is published in NeurIPS 2019.
Please cite our work using the BibTeX below.
@inproceedings{NEURIPS2019_6f2268bd,
author = {Santurkar, Shibani and Ilyas, Andrew and Tsipras, Dimitris and Engstrom, Logan and Tran, Brandon and Madry, Aleksander},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Image Synthesis with a Single (Robust) Classifier},
url = {https://proceedings.neurips.cc/paper/2019/file/6f2268bd1d3d3ebaabb04d6b5d099425-Paper.pdf},
volume = {32},
year = {2019}
}