{
  "id": "2208.00629",
  "version": "v1",
  "published": "2022-08-01T06:22:33.000Z",
  "updated": "2022-08-01T06:22:33.000Z",
  "title": "XOOD: Extreme Value Based Out-Of-Distribution Detection For Image Classification",
  "authors": [
    "Frej Berglind",
    "Haron Temam",
    "Supratik Mukhopadhyay",
    "Kamalika Das",
    "Md Saiful Islam Sajol",
    "Sricharan Kumar",
    "Kumar Kallurupalli"
  ],
  "categories": [
    "cs.LG",
    "cs.AI",
    "cs.CV"
  ],
  "abstract": "Detecting out-of-distribution (OOD) data at inference time is crucial for many applications of machine learning. We present XOOD: a novel extreme value-based OOD detection framework for image classification that consists of two algorithms. The first, XOOD-M, is completely unsupervised, while the second XOOD-L is self-supervised. Both algorithms rely on the signals captured by the extreme values of the data in the activation layers of the neural network in order to distinguish between in-distribution and OOD instances. We show experimentally that both XOOD-M and XOOD-L outperform state-of-the-art OOD detection methods on many benchmark data sets in both efficiency and accuracy, reducing false-positive rate (FPR95) by 50%, while improving the inferencing time by an order of magnitude.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-08-01T06:22:33.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "image classification",
      "out-of-distribution detection",
      "value-based ood detection framework",
      "extreme value-based ood detection",
      "outperform state-of-the-art ood detection methods"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}