Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder

by   Zhisheng Xiao, et al.
The University of Chicago

Deep probabilistic generative models enable modeling the likelihoods of very high dimensional data. An important application of generative modeling should be the ability to detect out-of-distribution (OOD) samples by setting a threshold on the likelihood. However, a recent study shows that probabilistic generative models can, in some cases, assign higher likelihoods on certain types of OOD samples, making the OOD detection rules based on likelihood threshold problematic. To address this issue, several OOD detection methods have been proposed for deep generative models. In this paper, we make the observation that some of these methods fail when applied to generative models based on Variational Auto-encoders (VAE). As an alternative, we propose Likelihood Regret, an efficient OOD score for VAEs. We benchmark our proposed method over existing approaches, and empirical results suggest that our method obtains the best overall OOD detection performances compared with other OOD method applied on VAE.


page 3

page 9

page 12

page 15

page 16

page 17


Unsupervised Out-of-Distribution Detection with Batch Normalization

Likelihood from a generative model is a natural statistic for detecting ...

Out-of-distribution Detection via Frequency-regularized Generative Models

Modern deep generative models can assign high likelihood to inputs drawn...

Out-of-Distribution Detection Using Neural Rendering Generative Models

Out-of-distribution (OoD) detection is a natural downstream task for dee...

Input complexity and out-of-distribution detection with likelihood-based generative models

Likelihood-based generative models are a promising resource to detect ou...

Robust Out-of-Distribution Detection on Deep Probabilistic Generative Models

Out-of-distribution (OOD) detection is an important task in machine lear...

A Test of Relative Similarity For Model Selection in Generative Models

Probabilistic generative models provide a powerful framework for represe...

Entropic Issues in Likelihood-Based OOD Detection

Deep generative models trained by maximum likelihood remain very popular...

Please sign up or login with your details

Forgot password? Click here to reset