Revisiting Energy-Based Model for Out-of-Distribution Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913596889366528 |
|---|---|
| author | Wu, Yifan Ye, Xichen Dai, Songmin Pan, Dengye Li, Xiaoqiang Zhang, Weizhong Chen, Yifan |
| author_facet | Wu, Yifan Ye, Xichen Dai, Songmin Pan, Dengye Li, Xiaoqiang Zhang, Weizhong Chen, Yifan |
| contents | Out-of-distribution (OOD) detection is an essential approach to robustifying deep learning models, enabling them to identify inputs that fall outside of their trained distribution. Existing OOD detection methods usually depend on crafted data, such as specific outlier datasets or elaborate data augmentations. While this is reasonable, the frequent mismatch between crafted data and OOD data limits model robustness and generalizability. In response to this issue, we introduce Outlier Exposure by Simple Transformations (OEST), a framework that enhances OOD detection by leveraging "peripheral-distribution" (PD) data. Specifically, PD data are samples generated through simple data transformations, thus providing an efficient alternative to manually curated outliers.
We adopt energy-based models (EBMs) to study PD data. We recognize the "energy barrier" in OOD detection, which characterizes the energy difference between in-distribution (ID) and OOD samples and eases detection. PD data are introduced to establish the energy barrier during training. Furthermore, this energy barrier concept motivates a theoretically grounded energy-barrier loss to replace the classical energy-bounded loss, leading to an improved paradigm, OEST*, which achieves a more effective and theoretically sound separation between ID and OOD samples. We perform empirical validation of our proposal, and extensive experiments across various benchmarks demonstrate that OEST* achieves better or similar accuracy compared with state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03058 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Revisiting Energy-Based Model for Out-of-Distribution Detection Wu, Yifan Ye, Xichen Dai, Songmin Pan, Dengye Li, Xiaoqiang Zhang, Weizhong Chen, Yifan Computer Vision and Pattern Recognition 68T05, 68T45 I.2.10; I.5.1 Out-of-distribution (OOD) detection is an essential approach to robustifying deep learning models, enabling them to identify inputs that fall outside of their trained distribution. Existing OOD detection methods usually depend on crafted data, such as specific outlier datasets or elaborate data augmentations. While this is reasonable, the frequent mismatch between crafted data and OOD data limits model robustness and generalizability. In response to this issue, we introduce Outlier Exposure by Simple Transformations (OEST), a framework that enhances OOD detection by leveraging "peripheral-distribution" (PD) data. Specifically, PD data are samples generated through simple data transformations, thus providing an efficient alternative to manually curated outliers. We adopt energy-based models (EBMs) to study PD data. We recognize the "energy barrier" in OOD detection, which characterizes the energy difference between in-distribution (ID) and OOD samples and eases detection. PD data are introduced to establish the energy barrier during training. Furthermore, this energy barrier concept motivates a theoretically grounded energy-barrier loss to replace the classical energy-bounded loss, leading to an improved paradigm, OEST*, which achieves a more effective and theoretically sound separation between ID and OOD samples. We perform empirical validation of our proposal, and extensive experiments across various benchmarks demonstrate that OEST* achieves better or similar accuracy compared with state-of-the-art methods. |
| title | Revisiting Energy-Based Model for Out-of-Distribution Detection |
| topic | Computer Vision and Pattern Recognition 68T05, 68T45 I.2.10; I.5.1 |
| url | https://arxiv.org/abs/2412.03058 |