[3N4-GS-7] Vision, speech media processing:

[3N4-GS-7-02] Inpainting-based Unsupervised Anomaly Detection with Diffusion Models

〇Shunsuke Sakai¹, Tatsuhito Hasegawa¹ (1. University of Fukui)

Keywords:Unsupervised Anomaly Detection, Diffusion Model, Masked Image Modeling, Density Estimation, Image Inpainting

Anomaly detection using conventional diffusion models takes an approach where a certain intensity of noise is added to the input image, and anomalies are removed by following the reverse diffusion process learned on normal images. However, this approach has the issue that the noise intensity significantly affects detection performance. In this study, we introduce a novel anomaly detection method using a diffusion model based on image inpainting to address this issue. In anomaly detection based on image inpainting, the masked regions are restored from complete noise, enabling stable detection performance independent of noise intensity. Furthermore, by employing an iterative mask update strategy based on reconstruction error, we improved detection performance compared to a random masking strategy. The proposed method was evaluated on MVTecAD and demonstrated superior performance compared to the baseline and existing anomaly detection methods based on image inpainting.