Anomaly detection through latent space restoration using vector-quantized variational autoencoders

TL;DR

This paper introduces a novel anomaly detection method using Vector-Quantized Variational Auto-Encoders that combines density estimation and image restoration, achieving higher accuracy on benchmark datasets.

Contribution

The paper presents a new unsupervised anomaly detection approach leveraging VQ-VAE and autoregressive models for improved detection and pixel-wise anomaly scoring.

Findings

Higher detection accuracy on MOOD datasets

Effective sample and pixel-wise anomaly scoring

Combines density and restoration methods for anomaly detection

Abstract

We propose an out-of-distribution detection method that combines density and restoration-based approaches using Vector-Quantized Variational Auto-Encoders (VQ-VAEs). The VQ-VAE model learns to encode images in a categorical latent space. The prior distribution of latent codes is then modelled using an Auto-Regressive (AR) model. We found that the prior probability estimated by the AR model can be useful for unsupervised anomaly detection and enables the estimation of both sample and pixel-wise anomaly scores. The sample-wise score is defined as the negative log-likelihood of the latent variables above a threshold selecting highly unlikely codes. Additionally, out-of-distribution images are restored into in-distribution images by replacing unlikely latent codes with samples from the prior model and decoding to pixel space. The average L1 distance between generated restorations and original image is used as pixel-wise anomaly score. We tested our approach on the MOOD challenge datasets, and report higher accuracies compared to a standard reconstruction-based approach with VAEs.