{
  "id": "2303.15361",
  "version": "v1",
  "published": "2023-03-27T16:32:21.000Z",
  "updated": "2023-03-27T16:32:21.000Z",
  "title": "A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts",
  "authors": [
    "Jian Liang",
    "Ran He",
    "Tieniu Tan"
  ],
  "comment": "Discussions, comments, and questions are all welcomed in \\url{https://github.com/tim-learn/awesome-test-time-adaptation}",
  "categories": [
    "cs.LG",
    "cs.AI",
    "cs.CV"
  ],
  "abstract": "Machine learning methods strive to acquire a robust model during training that can generalize well to test samples, even under distribution shifts. However, these methods often suffer from a performance drop due to unknown test distributions. Test-time adaptation (TTA), an emerging paradigm, has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions. Recent progress in this paradigm highlights the significant benefits of utilizing unlabeled data for training self-adapted models prior to inference. In this survey, we divide TTA into several distinct categories, namely, test-time (source-free) domain adaptation, test-time batch adaptation, online test-time adaptation, and test-time prior adaptation. For each category, we provide a comprehensive taxonomy of advanced algorithms, followed by a discussion of different learning scenarios. Furthermore, we analyze relevant applications of TTA and discuss open challenges and promising areas for future research. A comprehensive list of TTA methods can be found at \\url{https://github.com/tim-learn/awesome-test-time-adaptation}.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-03-27T16:32:21.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "distribution shifts",
      "comprehensive survey",
      "test-time prior adaptation",
      "online test-time adaptation",
      "unknown test distributions"
    ],
    "tags": [
      "github project"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}