{
  "id": "1912.03133",
  "version": "v1",
  "published": "2019-12-05T04:24:14.000Z",
  "updated": "2019-12-05T04:24:14.000Z",
  "title": "Why Should we Combine Training and Post-Training Methods for Out-of-Distribution Detection?",
  "authors": [
    "Aristotelis-Angelos Papadopoulos",
    "Nazim Shaikh",
    "Mohammad Reza Rajati"
  ],
  "comment": "Preprint, 9 pages. arXiv admin note: text overlap with arXiv:1906.03509",
  "categories": [
    "cs.LG",
    "cs.CV",
    "stat.ML"
  ],
  "abstract": "Deep neural networks are known to achieve superior results in classification tasks. However, it has been recently shown that they are incapable to detect examples that are generated by a distribution which is different than the one they have been trained on since they are making overconfident prediction for Out-Of-Distribution (OOD) examples. OOD detection has attracted a lot of attention recently. In this paper, we review some of the most seminal recent algorithms in the OOD detection field, we divide those methods into training and post-training and we experimentally show how the combination of the former with the latter can achieve state-of-the-art results in the OOD detection task.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-12-05T04:24:14.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "out-of-distribution detection",
      "post-training methods",
      "achieve superior results",
      "achieve state-of-the-art results",
      "ood detection field"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 9,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}