SPACE: SPAtial-aware Consistency rEgularization for anomaly detection in Industrial applications

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kim, Daehwan, Kim, Hyungmin, Jeong, Daun, Suh, Sungho, Cho, Hansang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909382185320448
author Kim, Daehwan
Kim, Hyungmin
Jeong, Daun
Suh, Sungho
Cho, Hansang
author_facet Kim, Daehwan
Kim, Hyungmin
Jeong, Daun
Suh, Sungho
Cho, Hansang
contents In this paper, we propose SPACE, a novel anomaly detection methodology that integrates a Feature Encoder (FE) into the structure of the Student-Teacher method. The proposed method has two key elements: Spatial Consistency regularization Loss (SCL) and Feature converter Module (FM). SCL prevents overfitting in student models by avoiding excessive imitation of the teacher model. Simultaneously, it facilitates the expansion of normal data features by steering clear of abnormal areas generated through data augmentation. This dual functionality ensures a robust boundary between normal and abnormal data. The FM prevents the learning of ambiguous information from the FE. This protects the learned features and enables more effective detection of structural and logical anomalies. Through these elements, SPACE is available to minimize the influence of the FE while integrating various data augmentations.In this study, we evaluated the proposed method on the MVTec LOCO, MVTec AD, and VisA datasets. Experimental results, through qualitative evaluation, demonstrate the superiority of detection and efficiency of each module compared to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2411_05822
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SPACE: SPAtial-aware Consistency rEgularization for anomaly detection in Industrial applications
Kim, Daehwan
Kim, Hyungmin
Jeong, Daun
Suh, Sungho
Cho, Hansang
Computer Vision and Pattern Recognition
In this paper, we propose SPACE, a novel anomaly detection methodology that integrates a Feature Encoder (FE) into the structure of the Student-Teacher method. The proposed method has two key elements: Spatial Consistency regularization Loss (SCL) and Feature converter Module (FM). SCL prevents overfitting in student models by avoiding excessive imitation of the teacher model. Simultaneously, it facilitates the expansion of normal data features by steering clear of abnormal areas generated through data augmentation. This dual functionality ensures a robust boundary between normal and abnormal data. The FM prevents the learning of ambiguous information from the FE. This protects the learned features and enables more effective detection of structural and logical anomalies. Through these elements, SPACE is available to minimize the influence of the FE while integrating various data augmentations.In this study, we evaluated the proposed method on the MVTec LOCO, MVTec AD, and VisA datasets. Experimental results, through qualitative evaluation, demonstrate the superiority of detection and efficiency of each module compared to state-of-the-art methods.
title SPACE: SPAtial-aware Consistency rEgularization for anomaly detection in Industrial applications
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.05822