EOOD: Entropy-based Out-of-distribution 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_ | 1866913776343711744 |
|---|---|
| author | Yang, Guide Hou, Chao Peng, Weilong Fang, Xiang Nie, Yongwei Zhu, Peican Tang, Keke |
| author_facet | Yang, Guide Hou, Chao Peng, Weilong Fang, Xiang Nie, Yongwei Zhu, Peican Tang, Keke |
| contents | Deep neural networks (DNNs) often exhibit overconfidence when encountering out-of-distribution (OOD) samples, posing significant challenges for deployment. Since DNNs are trained on in-distribution (ID) datasets, the information flow of ID samples through DNNs inevitably differs from that of OOD samples. In this paper, we propose an Entropy-based Out-Of-distribution Detection (EOOD) framework. EOOD first identifies specific block where the information flow differences between ID and OOD samples are more pronounced, using both ID and pseudo-OOD samples. It then calculates the conditional entropy on the selected block as the OOD confidence score. Comprehensive experiments conducted across various ID and OOD settings demonstrate the effectiveness of EOOD in OOD detection and its superiority over state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03342 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EOOD: Entropy-based Out-of-distribution Detection Yang, Guide Hou, Chao Peng, Weilong Fang, Xiang Nie, Yongwei Zhu, Peican Tang, Keke Computer Vision and Pattern Recognition Artificial Intelligence Deep neural networks (DNNs) often exhibit overconfidence when encountering out-of-distribution (OOD) samples, posing significant challenges for deployment. Since DNNs are trained on in-distribution (ID) datasets, the information flow of ID samples through DNNs inevitably differs from that of OOD samples. In this paper, we propose an Entropy-based Out-Of-distribution Detection (EOOD) framework. EOOD first identifies specific block where the information flow differences between ID and OOD samples are more pronounced, using both ID and pseudo-OOD samples. It then calculates the conditional entropy on the selected block as the OOD confidence score. Comprehensive experiments conducted across various ID and OOD settings demonstrate the effectiveness of EOOD in OOD detection and its superiority over state-of-the-art methods. |
| title | EOOD: Entropy-based Out-of-distribution Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2504.03342 |