Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation
This work addresses anomaly detection and segmentation for industrial applications, representing an incremental improvement over existing methods.
The paper tackles image anomaly detection and segmentation by extending a deep learning variant of Support Vector Data Description to a patch-based method using self-supervised learning, resulting in AUROC improvements of 9.8% for detection and 7.0% for segmentation on the MVTec AD dataset compared to previous state-of-the-art methods.
In this paper, we address the problem of image anomaly detection and segmentation. Anomaly detection involves making a binary decision as to whether an input image contains an anomaly, and anomaly segmentation aims to locate the anomaly on the pixel level. Support vector data description (SVDD) is a long-standing algorithm used for an anomaly detection, and we extend its deep learning variant to the patch-based method using self-supervised learning. This extension enables anomaly segmentation and improves detection performance. As a result, anomaly detection and segmentation performances measured in AUROC on MVTec AD dataset increased by 9.8% and 7.0%, respectively, compared to the previous state-of-the-art methods. Our results indicate the efficacy of the proposed method and its potential for industrial application. Detailed analysis of the proposed method offers insights regarding its behavior, and the code is available online.