Image synthesis with a single (robust) classifier

Santurkar, S; Tsipras, D; Tran, B; Ilyas, A; Engstrom, L; Madry, A

This is not the latest version of this item. The latest version can be found here.

Image synthesis with a single (robust) classifier

Download

Name

NeurIPS-2019-image-synthesis-with-a-single-robust-classifier-Paper.pdf

Description

Published version

Size

5.97 MB

Format

Adobe PDF

Checksum (MD5)

9be9d9d94d68576c57b3ad1baad13390

sword-2021-02-02T14:33:08.original.xml (130 B)

Original SWORD entry document

Author(s)

Santurkar, S

•

Tsipras, D

•

Tran, B

•

Ilyas, A

•

Engstrom, L

•

Madry, A

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,.

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

https://hdl.handle.net/1721.1/137494

DOI of Published Version

https://papers.nips.cc/paper/2019/hash/6f2268bd1d3d3ebaabb04d6b5d099425-Abstract.html