HomographyAD: Deep Anomaly Detection Using Self Homography Learning

TL;DR

HomographyAD introduces a deep learning-based anomaly detection method that leverages self homography learning and foreground alignment to improve detection accuracy in real-world industrial datasets.

Contribution

It proposes a novel anomaly detection approach using self homography learning and foreground alignment, tailored for actual industrial environments.

Findings

Enhanced anomaly detection performance on industrial datasets.

Effective use of self homography learning for shape information.

Performance improvements across various existing AD methods.

Abstract

Anomaly detection (AD) is a task that distinguishes normal and abnormal data, which is important for applying automation technologies of the manufacturing facilities. For MVTec dataset that is a representative AD dataset for industrial environment, many recent works have shown remarkable performances. However, the existing anomaly detection works have a limitation of showing good performance for fully-aligned datasets only, unlike real-world industrial environments. To solve this limitation, we propose HomographyAD, a novel deep anomaly detection methodology based on the ImageNet-pretrained network, which is specially designed for actual industrial dataset. Specifically, we first suggest input foreground alignment using the deep homography estimation method. In addition, we fine-tune the model by self homography learning to learn additional shape information from normal samples. Finally, we conduct anomaly detection based on the measure of how far the feature of test sample is from the distribution of the extracted normal features. By applying our proposed method to various existing AD approaches, we show performance enhancement through extensive experiments.