{
  "id": "2106.03004",
  "version": "v1",
  "published": "2021-06-06T01:45:11.000Z",
  "updated": "2021-06-06T01:45:11.000Z",
  "title": "Exploring the Limits of Out-of-Distribution Detection",
  "authors": [
    "Stanislav Fort",
    "Jie Ren",
    "Balaji Lakshminarayanan"
  ],
  "comment": "S.F. and J.R. contributed equally",
  "categories": [
    "cs.LG"
  ],
  "abstract": "Near out-of-distribution detection (OOD) is a major challenge for deep neural networks. We demonstrate that large-scale pre-trained transformers can significantly improve the state-of-the-art (SOTA) on a range of near OOD tasks across different data modalities. For instance, on CIFAR-100 vs CIFAR-10 OOD detection, we improve the AUROC from 85% (current SOTA) to more than 96% using Vision Transformers pre-trained on ImageNet-21k. On a challenging genomics OOD detection benchmark, we improve the AUROC from 66% to 77% using transformers and unsupervised pre-training. To further improve performance, we explore the few-shot outlier exposure setting where a few examples from outlier classes may be available; we show that pre-trained transformers are particularly well-suited for outlier exposure, and that the AUROC of OOD detection on CIFAR-100 vs CIFAR-10 can be improved to 98.7% with just 1 image per OOD class, and 99.46% with 10 images per OOD class. For multi-modal image-text pre-trained transformers such as CLIP, we explore a new way of using just the names of outlier classes as a sole source of information without any accompanying images, and show that this outperforms previous SOTA on standard vision OOD benchmark tasks.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-06-06T01:45:11.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "out-of-distribution detection",
      "genomics ood detection benchmark",
      "standard vision ood benchmark tasks",
      "pre-trained transformers",
      "ood class"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}