Year: 2019
Type: preprint
Abstract: 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. Code and models for our experiments can be found at https://git.io/robust-apps.
Source: arXiv (Cornell University)
Institution: Massachusetts Institute of Technology
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: US-Israel Collaboration: Collaborative Research: New Tools for Extracting Neuronal Phenotypes from a Volumetric Set of Cerebral Cortex Images, CAREER: Fast Graph Algorithms and Continuous Optimization, SaTC: CORE: Small: Towards Adversarially Robust Machine Learning, TWC: TTP Option: Frontier: Collaborative: MACS: A Modular Approach to Cloud Security, SHF: Medium: Collaborative Research: Run-Time Support for Scalable Concurrent Programming, BIGDATA: IA: DKA: Collaborative Research: High-Thoughput Connectomics
OpenAlex ID: W2965470910
