Anomaly Detection with Conditioned Denoising Diffusion Models

TL;DR

This paper introduces DDAD, a novel anomaly detection method using conditioned denoising diffusion models that achieves state-of-the-art results by generating defectless reconstructions for effective anomaly localization.

Contribution

The paper proposes a new conditioned denoising diffusion process for image reconstruction in anomaly detection, incorporating domain adaptation for improved feature comparison.

Findings

Achieves 99.8% AUROC on MVTec dataset.

Achieves 98.9% AUROC on VisA dataset.

Outperforms existing methods in anomaly detection accuracy.

Abstract

Traditional reconstruction-based methods have struggled to achieve competitive performance in anomaly detection. In this paper, we introduce Denoising Diffusion Anomaly Detection (DDAD), a novel denoising process for image reconstruction conditioned on a target image. This ensures a coherent restoration that closely resembles the target image. Our anomaly detection framework employs the conditioning mechanism, where the target image is set as the input image to guide the denoising process, leading to a defectless reconstruction while maintaining nominal patterns. Anomalies are then localised via a pixel-wise and feature-wise comparison of the input and reconstructed image. Finally, to enhance the effectiveness of the feature-wise comparison, we introduce a domain adaptation method that utilises nearly identical generated examples from our conditioned denoising process to fine-tune the pretrained feature extractor. The veracity of DDAD is demonstrated on various datasets including MVTec and VisA benchmarks, achieving state-of-the-art results of \(99.8 \%\) and \(98.9 \%\) image-level AUROC respectively.