Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915381261631488 |
|---|---|
| author | Ding, Yifan Aleksandraus, Arturas Ahmadian, Amirhossein Unger, Jonas Lindsten, Fredrik Eilertsen, Gabriel |
| author_facet | Ding, Yifan Aleksandraus, Arturas Ahmadian, Amirhossein Unger, Jonas Lindsten, Fredrik Eilertsen, Gabriel |
| contents | Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning systems, particularly in safety-critical applications. Likelihood-based deep generative models have historically faced criticism for their unsatisfactory performance in OOD detection, often assigning higher likelihood to OOD data than in-distribution samples when applied to image data. In this work, we demonstrate that likelihood is not inherently flawed. Rather, several properties in the images space prohibit likelihood as a valid detection score. Given a sufficiently good likelihood estimator, specifically using the probability flow formulation of a diffusion model, we show that likelihood-based methods can still perform on par with state-of-the-art methods when applied in the representation space of pre-trained encoders. The code of our work can be found at $\href{https://github.com/limchaos/Likelihood-OOD.git}{\texttt{https://github.com/limchaos/Likelihood-OOD.git}}$. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07793 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations Ding, Yifan Aleksandraus, Arturas Ahmadian, Amirhossein Unger, Jonas Lindsten, Fredrik Eilertsen, Gabriel Machine Learning Computer Vision and Pattern Recognition Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning systems, particularly in safety-critical applications. Likelihood-based deep generative models have historically faced criticism for their unsatisfactory performance in OOD detection, often assigning higher likelihood to OOD data than in-distribution samples when applied to image data. In this work, we demonstrate that likelihood is not inherently flawed. Rather, several properties in the images space prohibit likelihood as a valid detection score. Given a sufficiently good likelihood estimator, specifically using the probability flow formulation of a diffusion model, we show that likelihood-based methods can still perform on par with state-of-the-art methods when applied in the representation space of pre-trained encoders. The code of our work can be found at $\href{https://github.com/limchaos/Likelihood-OOD.git}{\texttt{https://github.com/limchaos/Likelihood-OOD.git}}$. |
| title | Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.07793 |