Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection

TL;DR

This paper introduces a novel diffusion model framework with dynamic noise addition and latent space projection, significantly improving anomaly localization across various scales in image datasets.

Contribution

It extends implicit conditioning with dynamic step size, scaled input denoising, and latent space projection, enhancing diffusion models for better anomaly detection and localization.

Findings

Effective localization of anomalies of various sizes.

Superior performance on VisA, BTAD, and MVTec datasets.

Enhanced ability to detect large missing components.

Abstract

Diffusion models have found valuable applications in anomaly detection by capturing the nominal data distribution and identifying anomalies via reconstruction. Despite their merits, they struggle to localize anomalies of varying scales, especially larger anomalies such as entire missing components. Addressing this, we present a novel framework that enhances the capability of diffusion models, by extending the previous introduced implicit conditioning approach Meng et al. (2022) in three significant ways. First, we incorporate a dynamic step size computation that allows for variable noising steps in the forward process guided by an initial anomaly prediction. Second, we demonstrate that denoising an only scaled input, without any added noise, outperforms conventional denoising process. Third, we project images in a latent space to abstract away from fine details that interfere with reconstruction of large missing components. Additionally, we propose a fine-tuning mechanism that facilitates the model to effectively grasp the nuances of the target domain. Our method undergoes rigorous evaluation on prominent anomaly detection datasets VisA, BTAD and MVTec yielding strong performance. Importantly, our framework effectively localizes anomalies regardless of their scale, marking a pivotal advancement in diffusion-based anomaly detection.