{
  "id": "2311.13959",
  "version": "v1",
  "published": "2023-11-23T12:17:45.000Z",
  "updated": "2023-11-23T12:17:45.000Z",
  "title": "RankFeat\\&RankWeight: Rank-1 Feature/Weight Removal for Out-of-distribution Detection",
  "authors": [
    "Yue Song",
    "Nicu Sebe",
    "Wei Wang"
  ],
  "comment": "submitted to T-PAMI",
  "categories": [
    "cs.LG",
    "cs.CV"
  ],
  "abstract": "The task of out-of-distribution (OOD) detection is crucial for deploying machine learning models in real-world settings. In this paper, we observe that the singular value distributions of the in-distribution (ID) and OOD features are quite different: the OOD feature matrix tends to have a larger dominant singular value than the ID feature, and the class predictions of OOD samples are largely determined by it. This observation motivates us to propose \\texttt{RankFeat}, a simple yet effective \\emph{post hoc} approach for OOD detection by removing the rank-1 matrix composed of the largest singular value and the associated singular vectors from the high-level feature. \\texttt{RankFeat} achieves \\emph{state-of-the-art} performance and reduces the average false positive rate (FPR95) by 17.90\\% compared with the previous best method. The success of \\texttt{RankFeat} motivates us to investigate whether a similar phenomenon would exist in the parameter matrices of neural networks. We thus propose \\texttt{RankWeight} which removes the rank-1 weight from the parameter matrices of a single deep layer. Our \\texttt{RankWeight}is also \\emph{post hoc} and only requires computing the rank-1 matrix once. As a standalone approach, \\texttt{RankWeight} has very competitive performance against other methods across various backbones. Moreover, \\texttt{RankWeight} enjoys flexible compatibility with a wide range of OOD detection methods. The combination of \\texttt{RankWeight} and \\texttt{RankFeat} refreshes the new \\emph{state-of-the-art} performance, achieving the FPR95 as low as 16.13\\% on the ImageNet-1k benchmark. Extensive ablation studies and comprehensive theoretical analyses are presented to support the empirical results.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-11-23T12:17:45.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "out-of-distribution detection",
      "feature/weight removal",
      "parameter matrices",
      "ood detection",
      "ood feature matrix tends"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}