{
  "id": "1906.09453",
  "version": "v1",
  "published": "2019-06-06T09:12:08.000Z",
  "updated": "2019-06-06T09:12:08.000Z",
  "title": "Computer Vision with a Single (Robust) Classifier",
  "authors": [
    "Shibani Santurkar",
    "Dimitris Tsipras",
    "Brandon Tran",
    "Andrew Ilyas",
    "Logan Engstrom",
    "Aleksander Madry"
  ],
  "categories": [
    "cs.CV",
    "cs.LG",
    "cs.NE",
    "stat.ML"
  ],
  "abstract": "We show that the basic classification framework alone can be used to tackle some 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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-06-06T09:12:08.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "classifier",
      "broader machine learning context",
      "basic classification framework",
      "challenging computer vision tasks",
      "directly manipulate salient features"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}