Image synthesis with a single (robust) classifier
Name
NeurIPS-2019-image-synthesis-with-a-single-robust-classifier-Paper.pdf
Description
Published version
Size
5.97 MB
Format
Unknown
Checksum (MD5)
9be9d9d94d68576c57b3ad1baad13390
Author(s)
Santurkar, Shibani
Tsipras, Dimitris
Tran, Brandon
Ilyas, Andrew
Engstrom, Logan G.
Madry, Aleksander
Date Issued
2019
Journal
Advances in Neural Information Processing Systems
Citation
Santurkar, S, Tsipras, D, Tran, B, Ilyas, A, Engstrom, L et al. 2019. "Image synthesis with a single (robust) classifier." Advances in Neural Information Processing Systems, 32.
Version
Final published version
Abstract
© 2019 Neural information processing systems foundation. All rights reserved. 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-the-art approaches, the toolkit we develop is rather minimal: it uses a single, off-the-shelf 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.2,.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/2019/hash/6f2268bd1d3d3ebaabb04d6b5d099425-Abstract.html
