Domain-independent detection of known anomalies

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bühler, Jonas, Fehrenbach, Jonas, Steinmann, Lucas, Nauck, Christian, Koulakis, Marios
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916310474031104
author Bühler, Jonas
Fehrenbach, Jonas
Steinmann, Lucas
Nauck, Christian
Koulakis, Marios
author_facet Bühler, Jonas
Fehrenbach, Jonas
Steinmann, Lucas
Nauck, Christian
Koulakis, Marios
contents One persistent obstacle in industrial quality inspection is the detection of anomalies. In real-world use cases, two problems must be addressed: anomalous data is sparse and the same types of anomalies need to be detected on previously unseen objects. Current anomaly detection approaches can be trained with sparse nominal data, whereas domain generalization approaches enable detecting objects in previously unseen domains. Utilizing those two observations, we introduce the hybrid task of domain generalization on sparse classes. To introduce an accompanying dataset for this task, we present a modification of the well-established MVTec AD dataset by generating three new datasets. In addition to applying existing methods for benchmark, we design two embedding-based approaches, Spatial Embedding MLP (SEMLP) and Labeled PatchCore. Overall, SEMLP achieves the best performance with an average image-level AUROC of 87.2 % vs. 80.4 % by MIRO. The new and openly available datasets allow for further research to improve industrial anomaly detection.
format Preprint
id arxiv_https___arxiv_org_abs_2407_02910
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Domain-independent detection of known anomalies
Bühler, Jonas
Fehrenbach, Jonas
Steinmann, Lucas
Nauck, Christian
Koulakis, Marios
Computer Vision and Pattern Recognition
One persistent obstacle in industrial quality inspection is the detection of anomalies. In real-world use cases, two problems must be addressed: anomalous data is sparse and the same types of anomalies need to be detected on previously unseen objects. Current anomaly detection approaches can be trained with sparse nominal data, whereas domain generalization approaches enable detecting objects in previously unseen domains. Utilizing those two observations, we introduce the hybrid task of domain generalization on sparse classes. To introduce an accompanying dataset for this task, we present a modification of the well-established MVTec AD dataset by generating three new datasets. In addition to applying existing methods for benchmark, we design two embedding-based approaches, Spatial Embedding MLP (SEMLP) and Labeled PatchCore. Overall, SEMLP achieves the best performance with an average image-level AUROC of 87.2 % vs. 80.4 % by MIRO. The new and openly available datasets allow for further research to improve industrial anomaly detection.
title Domain-independent detection of known anomalies
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.02910