Out-of-Distribution Detection with Class Ratio Estimation

06/08/2022
by   Mingtian Zhang, et al.
24

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/23/2022

Falsehoods that ML researchers believe about OOD detection

An intuitive way to detect out-of-distribution (OOD) data is via the den...
research
05/23/2019

Deep density ratio estimation for change point detection

In this work, we propose new objective functions to train deep neural ne...
research
02/16/2021

Hierarchical VAEs Know What They Don't Know

Deep generative models have shown themselves to be state-of-the-art dens...
research
02/07/2020

Learning Implicit Generative Models with Theoretical Guarantees

We propose a unified framework for implicit generative modeling (UnifiGe...
research
07/14/2021

Understanding Failures in Out-of-Distribution Detection with Deep Generative Models

Deep generative models (DGMs) seem a natural fit for detecting out-of-di...
research
06/22/2020

Telescoping Density-Ratio Estimation

Density-ratio estimation via classification is a cornerstone of unsuperv...
research
12/07/2021

A Unified Framework for Multi-distribution Density Ratio Estimation

Binary density ratio estimation (DRE), the problem of estimating the rat...

Please sign up or login with your details

Forgot password? Click here to reset