Computer Vision with a Single (Robust) Classifier.
Year: 2019
Type: preprint
Abstract: We show that the basic classification framework alone can be used to tacklesome of the most challenging computer vision tasks. 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)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2970718407