Article
Version 2
This version is not peer-reviewed
Back to the Metrics: Exploration of Distance Metrics in Anomaly Detection
and
*
Version 1
: Received: 7 June 2024 / Approved: 7 June 2024 / Online: 10 June 2024 (09:20:06 CEST)
Version 2 : Received: 19 July 2024 / Approved: 21 July 2024 / Online: 22 July 2024 (10:00:44 CEST)
Version 2 : Received: 19 July 2024 / Approved: 21 July 2024 / Online: 22 July 2024 (10:00:44 CEST)
How to cite: Lin, Y.; Li, X. Back to the Metrics: Exploration of Distance Metrics in Anomaly Detection. Preprints 2024, 2024060529. https://doi.org/10.20944/preprints202406.0529.v2 Lin, Y.; Li, X. Back to the Metrics: Exploration of Distance Metrics in Anomaly Detection. Preprints 2024, 2024060529. https://doi.org/10.20944/preprints202406.0529.v2
Abstract
With increasing research focus on industrial anomaly detection, numerous methods have emerged in this domain. Notably, memory bank-based approaches, coupled with kNN distance metrics, have demonstrated remarkable performance in anomaly detection (AD) and anomaly segmentation (AS). However, upon examination of the Back to the Feature (BTF) method applied to the Mvtec-3D AD dataset, it was observed that while it exhibited exceptional segmentation performance, its detection performance was lacking. To address this discrepancy, this study base improves the implementation of BTF, especially the improvement of the anomaly score metric. It posits that different "clusters" necessitate distinct k values in kNN distance metrics. For simplify, this assumption is distilled into the proposition that AD and AS tasks impose differing requirements on the k value in kNN distance metrics. Consequently, the paper introduces the BTM method, which utilizes distinct distance metrics for AD and AS tasks. This innovative approach yields superior AD and AS performance (I-AUROC 93.0%, AURPO 96.9%, P-AUROC 99.5%), representing a substantial enhancement over the BTF method (I-AUROC 5.7% ↑, AURPO 0.5% ↑, P-AUROC 0.2% ↑).
Keywords
image anomaly detection; defect detection; industrial manufacturing; distance metrics; anomaly score distribution
Subject
Engineering, Industrial and Manufacturing Engineering
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment
