TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection

TL;DR

TransFusion introduces a novel transparency-based diffusion process for anomaly detection that iteratively enhances normal region reconstruction, achieving state-of-the-art results on manufacturing datasets.

Contribution

It reformulates the traditional two-stage anomaly detection into a single-stage iterative process with a transparency-based diffusion mechanism for improved accuracy.

Findings

Achieves 98.5% AUROC on VisA dataset

Achieves 99.2% AUROC on MVTec AD dataset

Outperforms existing methods in anomaly detection accuracy

Abstract

Surface anomaly detection is a vital component in manufacturing inspection. Current discriminative methods follow a two-stage architecture composed of a reconstructive network followed by a discriminative network that relies on the reconstruction output. Currently used reconstructive networks often produce poor reconstructions that either still contain anomalies or lack details in anomaly-free regions. Discriminative methods are robust to some reconstructive network failures, suggesting that the discriminative network learns a strong normal appearance signal that the reconstructive networks miss. We reformulate the two-stage architecture into a single-stage iterative process that allows the exchange of information between the reconstruction and localization. We propose a novel transparency-based diffusion process where the transparency of anomalous regions is progressively increased, restoring their normal appearance accurately while maintaining the appearance of anomaly-free regions using localization cues of previous steps. We implement the proposed process as TRANSparency DifFUSION (TransFusion), a novel discriminative anomaly detection method that achieves state-of-the-art performance on both the VisA and the MVTec AD datasets, with an image-level AUROC of 98.5% and 99.2%, respectively. Code: https://github.com/MaticFuc/ECCV_TransFusion