|国家预印本平台
首页|Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations

Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations

Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations

来源:Arxiv_logoArxiv
英文摘要

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 $\href{https://github.com/limchaos/Likelihood-OOD.git}{\texttt{https://github.com/limchaos/Likelihood-OOD.git}}$.

Yifan Ding、Arturas Aleksandrauskas、Amirhossein Ahmadian、Jonas Unger、Fredrik Lindsten、Gabriel Eilertsen

计算技术、计算机技术

Yifan Ding,Arturas Aleksandrauskas,Amirhossein Ahmadian,Jonas Unger,Fredrik Lindsten,Gabriel Eilertsen.Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations[EB/OL].(2025-04-10)[2025-05-21].https://arxiv.org/abs/2504.07793.点此复制

评论