Unsupervised Out-of-Distribution Detection by Restoring Lossy Inputs with Variational Autoencoder

TL;DR

This paper introduces a novel VAE-based score called Error Reduction for out-of-distribution detection, which improves detection by restoring lossy inputs and demonstrates effectiveness across various datasets.

Contribution

The paper proposes a new VAE-based method for OOD detection that restores lossy inputs, addressing limitations of previous likelihood-based approaches.

Findings

Effective OOD detection on multiple datasets

VAE with lossy inputs improves detection accuracy

Ablation studies show design choices impact performance

Abstract

Deep generative models have been demonstrated as problematic in the unsupervised out-of-distribution (OOD) detection task, where they tend to assign higher likelihoods to OOD samples. Previous studies on this issue are usually not applicable to the Variational Autoencoder (VAE). As a popular subclass of generative models, the VAE can be effective with a relatively smaller model size and be more stable and faster in training and inference, which can be more advantageous in real-world applications. In this paper, We propose a novel VAE-based score called Error Reduction (ER) for OOD detection, which is based on a VAE that takes a lossy version of the training set as inputs and the original set as targets. Experiments are carried out on various datasets to show the effectiveness of our method, we also present the effect of design choices with ablation experiments. Our code is available at: https://github.com/ZJLAB-AMMI/VAE4OOD.