{
  "id": "2305.16966",
  "version": "v1",
  "published": "2023-05-26T14:21:39.000Z",
  "updated": "2023-05-26T14:21:39.000Z",
  "title": "Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection",
  "authors": [
    "Marc Lafon",
    "Elias Ramzi",
    "Clément Rambour",
    "Nicolas Thome"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "Out-of-distribution (OOD) detection is a critical requirement for the deployment of deep neural networks. This paper introduces the HEAT model, a new post-hoc OOD detection method estimating the density of in-distribution (ID) samples using hybrid energy-based models (EBM) in the feature space of a pre-trained backbone. HEAT complements prior density estimators of the ID density, e.g. parametric models like the Gaussian Mixture Model (GMM), to provide an accurate yet robust density estimation. A second contribution is to leverage the EBM framework to provide a unified density estimation and to compose several energy terms. Extensive experiments demonstrate the significance of the two contributions. HEAT sets new state-of-the-art OOD detection results on the CIFAR-10 / CIFAR-100 benchmark as well as on the large-scale Imagenet benchmark. The code is available at: https://github.com/MarcLafon/heat_ood.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-05-26T14:21:39.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "feature space",
      "hybrid energy",
      "out-of-distribution detection",
      "ood detection method estimating",
      "heat complements prior density estimators"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}