SA-PatchCore: Anomaly Detection in Dataset With Co-Occurrence Relationships Using Self-Attention

Abstract

Various unsupervised anomaly detection methods using deep learning have recently been proposed, and the accuracy of the anomaly detection technique for local anomalies has been improved. However, no anomaly detection dataset includes co-occurrence-related anomalies, which are combinationrelated. Thus, the accuracy of anomaly detection for co-occurrence-related anomalies has not progressed. Therefore, we propose SA-PatchCore, which introduces self-attention to the state-of-the-art local anomaly detection model, PatchCore. It detects anomalies in co-occurrence relationships and anomalies in local areas with the benefit of the self-attention module, which can consider contexts between separated words introduced first in the natural language processing field. As no anomaly detection dataset includes anomalies in co-occurrence relation, we prepared a new dataset called the Co-occurrence Anomaly Detection Screw Dataset (CAD-SD). Furthermore, we performed experiments on anomaly detection using the new dataset. SA-PatchCore achieves high anomaly detection performance compared with PatchCore in the CAD-SD. Moreover, our proposed model shows almost the same anomaly detection performance as PatchCore in an MVTec Anomaly Detection dataset, which is composed of anomalies in a local area. As a contribution to the anomaly detection task, we have released the CAD-SD to the public. This dataset can be downloaded from the following link: https://github.com/IshidaKengo/Co-occurrence-Anomaly-Detection-Screw-Dataset INDEX TERMS Anomaly detection, deep learning, self-attention

Intelligent Online Inspection of the Paste Quality of Prebaked Carbon Anodes Using an Anomaly Detection Algorithm

“…This latest image anomaly detection method shows great advantages in the industrial cold start-up process. Ishida et al [21] proposed SA-PatchCore to detect anomalies in co-occurrence relationships and local areas via a self-attention module based on PatchCore. In recent years, generative models have also been used in anomaly detection due to the advantage of being able to generate samples.…”