Unsupervised Anomaly Detection via Masked Diffusion Posterior Sampling

TL;DR

This paper introduces Masked Diffusion Posterior Sampling (MDPS), a novel method for unsupervised anomaly detection that leverages diffusion models with a Bayesian framework for improved reconstruction and localization.

Contribution

The paper proposes a mathematically grounded diffusion-based approach with a masked noisy observation model, enhancing interpretability and performance in anomaly detection.

Findings

Achieves state-of-the-art anomaly detection performance

Provides high-quality normal image reconstruction

Effective in anomaly localization on benchmark datasets

Abstract

Reconstruction-based methods have been commonly used for unsupervised anomaly detection, in which a normal image is reconstructed and compared with the given test image to detect and locate anomalies. Recently, diffusion models have shown promising applications for anomaly detection due to their powerful generative ability. However, these models lack strict mathematical support for normal image reconstruction and unexpectedly suffer from low reconstruction quality. To address these issues, this paper proposes a novel and highly-interpretable method named Masked Diffusion Posterior Sampling (MDPS). In MDPS, the problem of normal image reconstruction is mathematically modeled as multiple diffusion posterior sampling for normal images based on the devised masked noisy observation model and the diffusion-based normal image prior under Bayesian framework. Using a metric designed from pixel-level and perceptual-level perspectives, MDPS can effectively compute the difference map between each normal posterior sample and the given test image. Anomaly scores are obtained by averaging all difference maps for multiple posterior samples. Exhaustive experiments on MVTec and BTAD datasets demonstrate that MDPS can achieve state-of-the-art performance in normal image reconstruction quality as well as anomaly detection and localization.