NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915400345714688 |
|---|---|
| author | Ansari, Amirhossein Wang, Ke Xiong, Pulei |
| author_facet | Ansari, Amirhossein Wang, Ke Xiong, Pulei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09795 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection Ansari, Amirhossein Wang, Ke Xiong, Pulei Computer Vision and Pattern Recognition Machine Learning 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. |
| title | NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2507.09795 |