{"ID":2895309,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.09795","arxiv_id":"2507.09795","title":"NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection","abstract":"Recent advancements in Vision-Language Models like CLIP have enabled zero-shot OOD detection by leveraging both image and textual label information. Among these, negative label-based methods such as NegLabel and CSP have shown promising results by utilizing a lexicon of words to define negative labels for distinguishing OOD samples. However, these methods suffer from detecting in-distribution samples as OOD due to negative labels that are subcategories of in-distribution labels or proper nouns. They also face limitations in handling images that match multiple in-distribution and negative labels. We propose NegRefine, a novel negative label refinement framework for zero-shot OOD detection. By introducing a filtering mechanism to exclude subcategory labels and proper nouns from the negative label set and incorporating a multi-matching-aware scoring function that dynamically adjusts the contributions of multiple labels matching an image, NegRefine ensures a more robust separation between in-distribution and OOD samples. We evaluate NegRefine on large-scale benchmarks, including ImageNet-1K. The code is available at https://github.com/ah-ansari/NegRefine.","short_abstract":"Recent advancements in Vision-Language Models like CLIP have enabled zero-shot OOD detection by leveraging both image and textual label information. Among these, negative label-based methods such as NegLabel and CSP have shown promising results by utilizing a lexicon of words to define negative labels for distinguishin...","url_abs":"https://arxiv.org/abs/2507.09795","url_pdf":"https://arxiv.org/pdf/2507.09795v2","authors":"[\"Amirhossein Ansari\",\"Ke Wang\",\"Pulei Xiong\"]","published":"2025-07-13T21:15:30Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false,"code_links":[{"ID":612175,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2895309,"paper_url":"https://arxiv.org/abs/2507.09795","paper_title":"NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection","repo_url":"https://github.com/ah-ansari/NegRefine","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}