Image synthesis with a single (robust) classifier
Author(s)Santurkar, Shibani; Tsipras, Dimitris; Tran, Brandon; Ilyas, Andrew; Engstrom, Logan G.; Madry, Aleksander; ... Show more Show less
MetadataShow full item record
© 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,.
DepartmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Advances in Neural Information Processing Systems
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.
Final published version