LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection

The utilization of prior knowledge about anomalies is an essential issue for anomaly detections. Recently, the visual attention mechanism has become a promising way to improve the performance of CNNs for some computer vision tasks. In this paper, we propose a novel model called Layer-wise External A...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2021-09
Hauptverfasser: Katafuchi, Ryoya, Tokunaga, Terumasa
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Katafuchi, Ryoya
Tokunaga, Terumasa
description The utilization of prior knowledge about anomalies is an essential issue for anomaly detections. Recently, the visual attention mechanism has become a promising way to improve the performance of CNNs for some computer vision tasks. In this paper, we propose a novel model called Layer-wise External Attention Network (LEA-Net) for efficient image anomaly detection. The core idea relies on the integration of unsupervised and supervised anomaly detectors via the visual attention mechanism. Our strategy is as follows: (i) Prior knowledge about anomalies is represented as the anomaly map generated by unsupervised learning of normal instances, (ii) The anomaly map is translated to an attention map by the external network, (iii) The attention map is then incorporated into intermediate layers of the anomaly detection network. Notably, this layer-wise external attention can be applied to any CNN model in an end-to-end training manner. For a pilot study, we validate LEA-Net on color anomaly detection tasks. Through extensive experiments on PlantVillage, MVTec AD, and Cloud datasets, we demonstrate that the proposed layer-wise visual attention mechanism consistently boosts anomaly detection performances of an existing CNN model, even on imbalanced datasets. Moreover, we show that our attention mechanism successfully boosts the performance of several CNN models.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2572356786</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2572356786</sourcerecordid><originalsourceid>FETCH-proquest_journals_25723567863</originalsourceid><addsrcrecordid>eNqNzUELgjAcBfARBEn5HQadB7Y1lW5iiw7SyXsM-Q9ma6ttYn77FPoAnR6P94O3Qgll7EDKI6UblIbQZ1lG84JyzhLUNqIiN4gn3MgJPBl1ACw-EbyVBlcxgo3aWTyT0fkHVs5joZTu9Dzg2pm5V9Y9pZnwGSJ0i96htZImQPrLLdpfRFtfycu79wAh3ns3LAfhTnlBGc-LMmf_qS_5qz_H</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2572356786</pqid></control><display><type>article</type><title>LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection</title><source>Free E- Journals</source><creator>Katafuchi, Ryoya ; Tokunaga, Terumasa</creator><creatorcontrib>Katafuchi, Ryoya ; Tokunaga, Terumasa</creatorcontrib><description>The utilization of prior knowledge about anomalies is an essential issue for anomaly detections. Recently, the visual attention mechanism has become a promising way to improve the performance of CNNs for some computer vision tasks. In this paper, we propose a novel model called Layer-wise External Attention Network (LEA-Net) for efficient image anomaly detection. The core idea relies on the integration of unsupervised and supervised anomaly detectors via the visual attention mechanism. Our strategy is as follows: (i) Prior knowledge about anomalies is represented as the anomaly map generated by unsupervised learning of normal instances, (ii) The anomaly map is translated to an attention map by the external network, (iii) The attention map is then incorporated into intermediate layers of the anomaly detection network. Notably, this layer-wise external attention can be applied to any CNN model in an end-to-end training manner. For a pilot study, we validate LEA-Net on color anomaly detection tasks. Through extensive experiments on PlantVillage, MVTec AD, and Cloud datasets, we demonstrate that the proposed layer-wise visual attention mechanism consistently boosts anomaly detection performances of an existing CNN model, even on imbalanced datasets. Moreover, we show that our attention mechanism successfully boosts the performance of several CNN models.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Anomalies ; Color ; Computer vision ; Datasets ; Knowledge representation ; Performance enhancement</subject><ispartof>arXiv.org, 2021-09</ispartof><rights>2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Katafuchi, Ryoya</creatorcontrib><creatorcontrib>Tokunaga, Terumasa</creatorcontrib><title>LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection</title><title>arXiv.org</title><description>The utilization of prior knowledge about anomalies is an essential issue for anomaly detections. Recently, the visual attention mechanism has become a promising way to improve the performance of CNNs for some computer vision tasks. In this paper, we propose a novel model called Layer-wise External Attention Network (LEA-Net) for efficient image anomaly detection. The core idea relies on the integration of unsupervised and supervised anomaly detectors via the visual attention mechanism. Our strategy is as follows: (i) Prior knowledge about anomalies is represented as the anomaly map generated by unsupervised learning of normal instances, (ii) The anomaly map is translated to an attention map by the external network, (iii) The attention map is then incorporated into intermediate layers of the anomaly detection network. Notably, this layer-wise external attention can be applied to any CNN model in an end-to-end training manner. For a pilot study, we validate LEA-Net on color anomaly detection tasks. Through extensive experiments on PlantVillage, MVTec AD, and Cloud datasets, we demonstrate that the proposed layer-wise visual attention mechanism consistently boosts anomaly detection performances of an existing CNN model, even on imbalanced datasets. Moreover, we show that our attention mechanism successfully boosts the performance of several CNN models.</description><subject>Anomalies</subject><subject>Color</subject><subject>Computer vision</subject><subject>Datasets</subject><subject>Knowledge representation</subject><subject>Performance enhancement</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNzUELgjAcBfARBEn5HQadB7Y1lW5iiw7SyXsM-Q9ma6ttYn77FPoAnR6P94O3Qgll7EDKI6UblIbQZ1lG84JyzhLUNqIiN4gn3MgJPBl1ACw-EbyVBlcxgo3aWTyT0fkHVs5joZTu9Dzg2pm5V9Y9pZnwGSJ0i96htZImQPrLLdpfRFtfycu79wAh3ns3LAfhTnlBGc-LMmf_qS_5qz_H</recordid><startdate>20210912</startdate><enddate>20210912</enddate><creator>Katafuchi, Ryoya</creator><creator>Tokunaga, Terumasa</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210912</creationdate><title>LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection</title><author>Katafuchi, Ryoya ; Tokunaga, Terumasa</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25723567863</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Anomalies</topic><topic>Color</topic><topic>Computer vision</topic><topic>Datasets</topic><topic>Knowledge representation</topic><topic>Performance enhancement</topic><toplevel>online_resources</toplevel><creatorcontrib>Katafuchi, Ryoya</creatorcontrib><creatorcontrib>Tokunaga, Terumasa</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Katafuchi, Ryoya</au><au>Tokunaga, Terumasa</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection</atitle><jtitle>arXiv.org</jtitle><date>2021-09-12</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>The utilization of prior knowledge about anomalies is an essential issue for anomaly detections. Recently, the visual attention mechanism has become a promising way to improve the performance of CNNs for some computer vision tasks. In this paper, we propose a novel model called Layer-wise External Attention Network (LEA-Net) for efficient image anomaly detection. The core idea relies on the integration of unsupervised and supervised anomaly detectors via the visual attention mechanism. Our strategy is as follows: (i) Prior knowledge about anomalies is represented as the anomaly map generated by unsupervised learning of normal instances, (ii) The anomaly map is translated to an attention map by the external network, (iii) The attention map is then incorporated into intermediate layers of the anomaly detection network. Notably, this layer-wise external attention can be applied to any CNN model in an end-to-end training manner. For a pilot study, we validate LEA-Net on color anomaly detection tasks. Through extensive experiments on PlantVillage, MVTec AD, and Cloud datasets, we demonstrate that the proposed layer-wise visual attention mechanism consistently boosts anomaly detection performances of an existing CNN model, even on imbalanced datasets. Moreover, we show that our attention mechanism successfully boosts the performance of several CNN models.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2021-09
issn 2331-8422
language eng
recordid cdi_proquest_journals_2572356786
source Free E- Journals
subjects Anomalies
Color
Computer vision
Datasets
Knowledge representation
Performance enhancement
title LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T21%3A44%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=LEA-Net:%20Layer-wise%20External%20Attention%20Network%20for%20Efficient%20Color%20Anomaly%20Detection&rft.jtitle=arXiv.org&rft.au=Katafuchi,%20Ryoya&rft.date=2021-09-12&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2572356786%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2572356786&rft_id=info:pmid/&rfr_iscdi=true