{
  "id": "2206.09385",
  "version": "v1",
  "published": "2022-06-19T12:03:33.000Z",
  "updated": "2022-06-19T12:03:33.000Z",
  "title": "Out-of-distribution Detection by Cross-class Vicinity Distribution of In-distribution Data",
  "authors": [
    "Zhilin Zhao",
    "Longbing Cao",
    "Kun-Yu Lin"
  ],
  "categories": [
    "cs.LG"
  ],
  "abstract": "Deep neural networks only learn to map in-distribution inputs to their corresponding ground truth labels in the training phase without differentiating out-of-distribution samples from in-distribution ones. This results from the assumption that all samples are independent and identically distributed without distributional distinction. Therefore, a pretrained network learned from the in-distribution samples treats out-of-distribution samples as in-distribution and makes high-confidence predictions on them in the test phase. To address this issue, we draw out-of-distribution samples from the vicinity distribution of training in-distribution samples for learning to reject the prediction on out-of-distribution inputs. A \\textit{Cross-class Vicinity Distribution} is introduced by assuming that an out-of-distribution sample generated by mixing multiple in-distribution samples does not share the same classes of its constituents. We thus improve the discriminability of a pretrained network by finetuning it with out-of-distribution samples drawn from the cross-class vicinity distribution, where each out-of-distribution input corresponds to a complementary label. Experiments on various in-/out-of-distribution datasets show that the proposed method significantly outperforms existing methods in improving the capacity of discriminating between in- and out-of-distribution samples.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-06-19T12:03:33.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "cross-class vicinity distribution",
      "in-distribution data",
      "out-of-distribution detection",
      "significantly outperforms existing methods",
      "in-distribution samples treats out-of-distribution samples"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}