Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization

TL;DR

This paper introduces collaborative discrepancy optimization (CDO), a method that enhances image anomaly localization by reducing overgeneralization through optimizing the discrepancy distributions of normal and abnormal features.

Contribution

The paper proposes a novel CDO approach with margin and overlap optimization modules to improve anomaly localization accuracy and reliability.

Findings

Effective mitigation of overgeneralization in anomaly detection

Achieves high localization accuracy on MVTec datasets

Demonstrates real-time performance and practical application

Abstract

Most unsupervised image anomaly localization methods suffer from overgeneralization because of the high generalization abilities of convolutional neural networks, leading to unreliable predictions. To mitigate the overgeneralization, this study proposes to collaboratively optimize normal and abnormal feature distributions with the assistance of synthetic anomalies, namely collaborative discrepancy optimization (CDO). CDO introduces a margin optimization module and an overlap optimization module to optimize the two key factors determining the localization performance, i.e., the margin and the overlap between the discrepancy distributions (DDs) of normal and abnormal samples. With CDO, a large margin and a small overlap between normal and abnormal DDs are obtained, and the prediction reliability is boosted. Experiments on MVTec2D and MVTec3D show that CDO effectively mitigates the overgeneralization and achieves great anomaly localization performance with real-time computation efficiency. A real-world automotive plastic parts inspection application further demonstrates the capability of the proposed CDO. Code is available on https://github.com/caoyunkang/CDO.