{
  "id": "2308.13792",
  "version": "v1",
  "published": "2023-08-26T07:35:16.000Z",
  "updated": "2023-08-26T07:35:16.000Z",
  "title": "Out-of-distribution detection using normalizing flows on the data manifold",
  "authors": [
    "Seyedeh Fatemeh Razavi",
    "Mohammad Mahdi Mehmanchi",
    "Reshad Hosseini",
    "Mostafa Tavassolipour"
  ],
  "categories": [
    "cs.LG",
    "cs.CV"
  ],
  "abstract": "A common approach for out-of-distribution detection involves estimating an underlying data distribution, which assigns a lower likelihood value to out-of-distribution data. Normalizing flows are likelihood-based generative models providing a tractable density estimation via dimension-preserving invertible transformations. Conventional normalizing flows are prone to fail in out-of-distribution detection, because of the well-known curse of dimensionality problem of the likelihood-based models. According to the manifold hypothesis, real-world data often lie on a low-dimensional manifold. This study investigates the effect of manifold learning using normalizing flows on out-of-distribution detection. We proceed by estimating the density on a low-dimensional manifold, coupled with measuring the distance from the manifold, as criteria for out-of-distribution detection. However, individually, each of them is insufficient for this task. The extensive experimental results show that manifold learning improves the out-of-distribution detection ability of a class of likelihood-based models known as normalizing flows. This improvement is achieved without modifying the model structure or using auxiliary out-of-distribution data during training.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-08-26T07:35:16.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "data manifold",
      "low-dimensional manifold",
      "likelihood-based models",
      "out-of-distribution detection ability",
      "auxiliary out-of-distribution data"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}