LogicAL: Towards logical anomaly synthesis for unsupervised anomaly localization

TL;DR

LogicAL is a novel framework that synthesizes both logical and structural anomalies using edge manipulation, significantly enhancing unsupervised anomaly localization in industrial settings.

Contribution

It introduces a new edge manipulation based anomaly synthesis method that generates realistic logical and structural anomalies, filling a gap in existing unsupervised approaches.

Findings

Outperforms existing methods on MVTecLOCO, MVTecAD, VisA, and MADsim datasets.

Effectively synthesizes both logical and structural anomalies.

Improves anomaly localization accuracy in industrial applications.

Abstract

Anomaly localization is a practical technology for improving industrial production line efficiency. Due to anomalies are manifold and hard to be collected, existing unsupervised researches are usually equipped with anomaly synthesis methods. However, most of them are biased towards structural defects synthesis while ignoring the underlying logical constraints. To fill the gap and boost anomaly localization performance, we propose an edge manipulation based anomaly synthesis framework, named LogicAL, that produces photo-realistic both logical and structural anomalies. We introduce a logical anomaly generation strategy that is adept at breaking logical constraints and a structural anomaly generation strategy that complements to the structural defects synthesis. We further improve the anomaly localization performance by introducing edge reconstruction into the network structure. Extensive experiments on the challenge MVTecLOCO, MVTecAD, VisA and MADsim datasets verify the advantage of proposed LogicAL on both logical and structural anomaly localization.