Learning with Adaptive Prototype Manifolds for Out-of-Distribution Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914307500933120 |
|---|---|
| author | Peng, Ningkang Zhou, JiuTao Zhang, Yuhao Peng, Xiaoqian Yu, Qianfeng Qian, Linjing Lu, Tingyu Chen, Yi Gu, Yanhui |
| author_facet | Peng, Ningkang Zhou, JiuTao Zhang, Yuhao Peng, Xiaoqian Yu, Qianfeng Qian, Linjing Lu, Tingyu Chen, Yi Gu, Yanhui |
| contents | Out-of-distribution (OOD) detection is a critical task for the safe deployment of machine learning models in the real world. Existing prototype-based representation learning methods have demonstrated exceptional performance. Specifically, we identify two fundamental flaws that universally constrain these methods: the Static Homogeneity Assumption (fixed representational resources for all classes) and the Learning-Inference Disconnect (discarding rich prototype quality knowledge at inference). These flaws fundamentally limit the model's capacity and performance. To address these issues, we propose APEX (Adaptive Prototype for eXtensive OOD Detection), a novel OOD detection framework designed via a Two-Stage Repair process to optimize the learned feature manifold. APEX introduces two key innovations to address these respective flaws: (1) an Adaptive Prototype Manifold (APM), which leverages the Minimum Description Length (MDL) principle to automatically determine the optimal prototype complexity $K_c^*$ for each class, thereby fundamentally resolving prototype collision; and (2) a Posterior-Aware OOD Scoring (PAOS) mechanism, which quantifies prototype quality (cohesion and separation) to bridge the learning-inference disconnect. Comprehensive experiments on benchmarks such as CIFAR-100 validate the superiority of our method, where APEX achieves new state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05349 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning with Adaptive Prototype Manifolds for Out-of-Distribution Detection Peng, Ningkang Zhou, JiuTao Zhang, Yuhao Peng, Xiaoqian Yu, Qianfeng Qian, Linjing Lu, Tingyu Chen, Yi Gu, Yanhui Computer Vision and Pattern Recognition Out-of-distribution (OOD) detection is a critical task for the safe deployment of machine learning models in the real world. Existing prototype-based representation learning methods have demonstrated exceptional performance. Specifically, we identify two fundamental flaws that universally constrain these methods: the Static Homogeneity Assumption (fixed representational resources for all classes) and the Learning-Inference Disconnect (discarding rich prototype quality knowledge at inference). These flaws fundamentally limit the model's capacity and performance. To address these issues, we propose APEX (Adaptive Prototype for eXtensive OOD Detection), a novel OOD detection framework designed via a Two-Stage Repair process to optimize the learned feature manifold. APEX introduces two key innovations to address these respective flaws: (1) an Adaptive Prototype Manifold (APM), which leverages the Minimum Description Length (MDL) principle to automatically determine the optimal prototype complexity $K_c^*$ for each class, thereby fundamentally resolving prototype collision; and (2) a Posterior-Aware OOD Scoring (PAOS) mechanism, which quantifies prototype quality (cohesion and separation) to bridge the learning-inference disconnect. Comprehensive experiments on benchmarks such as CIFAR-100 validate the superiority of our method, where APEX achieves new state-of-the-art performance. |
| title | Learning with Adaptive Prototype Manifolds for Out-of-Distribution Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.05349 |