{
  "id": "2406.00345",
  "version": "v1",
  "published": "2024-06-01T07:46:42.000Z",
  "updated": "2024-06-01T07:46:42.000Z",
  "title": "DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection",
  "authors": [
    "Zhi Zhou",
    "Ming Yang",
    "Jiang-Xin Shi",
    "Lan-Zhe Guo",
    "Yu-Feng Li"
  ],
  "comment": "Accepted by ICML 2024. Code is available at: https://wnjxyk.github.io/DeCoOp",
  "categories": [
    "cs.CV",
    "cs.LG"
  ],
  "abstract": "Vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot capabilities for various downstream tasks. Their performance can be further enhanced through few-shot prompt tuning methods. However, current studies evaluate the performance of learned prompts separately on base and new classes. This evaluation lacks practicality for real-world applications since downstream tasks cannot determine whether the data belongs to base or new classes in advance. In this paper, we explore a problem setting called Open-world Prompt Tuning (OPT), which involves tuning prompts on base classes and evaluating on a combination of base and new classes. By introducing Decomposed Prompt Tuning framework (DePT), we theoretically demonstrate that OPT can be solved by incorporating out-of-distribution detection into prompt tuning, thereby enhancing the base-to-new discriminability. Based on DePT, we present a novel prompt tuning approach, namely, Decomposed Context Optimization (DeCoOp), which introduces new-class detectors and sub-classifiers to further enhance the base-class and new-class discriminability. Experimental results on 11 benchmark datasets validate the effectiveness of DePT and demonstrate that DeCoOp outperforms current state-of-the-art methods, providing a significant 2% average accuracy improvement.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-06-01T07:46:42.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "out-of-distribution detection",
      "robust prompt tuning",
      "decomposed prompt tuning framework",
      "decoop outperforms current state-of-the-art methods",
      "downstream tasks"
    ],
    "tags": [
      "github project"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}