Out-of-Distribution Detection with Class Ratio Estimation

• URL: http://arxiv.org/abs/2206.03955v1
• Date: Wed, 8 Jun 2022 15:20:49 GMT
• Title: Out-of-Distribution Detection with Class Ratio Estimation
• Authors: Mingtian Zhang and Andi Zhang and Tim Z. Xiao and Yitong Sun and Steven McDonagh
• Abstract summary: Density-based Out-of-distribution (OOD) detection has recently been shown unreliable for the task of detecting OOD images. We propose to unify density ratio based methods under a novel framework that builds energy-based models and employs differing base distributions.
• Score: 4.930817402876787
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Density-based Out-of-distribution (OOD) detection has recently been shown unreliable for the task of detecting OOD images. Various density ratio based approaches achieve good empirical performance, however methods typically lack a principled probabilistic modelling explanation. In this work, we propose to unify density ratio based methods under a novel framework that builds energy-based models and employs differing base distributions. Under our framework, the density ratio can be viewed as the unnormalized density of an implicit semantic distribution. Further, we propose to directly estimate the density ratio of a data sample through class ratio estimation. We report competitive results on OOD image problems in comparison with recent work that alternatively requires training of deep generative models for the task. Our approach enables a simple and yet effective path towards solving the OOD detection problem.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.