| アイテムタイプ |
共通アイテムタイプ(1) |
| 公開日 |
2025-03-19 |
| タイトル |
|
|
タイトル |
Layer-wise External Attention for Efficient Deep Anomaly Detection |
|
言語 |
en |
| 著者 |
Hayakawa, Tokihisa
Nakanishi, Keiichi
Katafuchi, Ryoya
徳永, 旭将
|
| 著作権関連情報 |
|
|
権利情報Resource |
https://creativecommons.org/licenses/by-nc-nd/4.0/ |
|
権利情報 |
Copyright (c) 2023 by SCITEPRESS – Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0) |
|
言語 |
en |
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Recently, the visual attention mechanism has become a promising way to improve the performance of Convolutional Neural Networks (CNNs) for many applications. In this paper, we propose a Layer-wise External Attention mechanism for efficient image anomaly detection. The core idea is 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 an anomaly map generated by the pre-trained network; (ii) the anomaly map is translated to an attention map via an external network. (iii) the attention map is then incorporated into intermediate layers of the anomaly detection network via visual attention. Notably, the proposed method can be applied to any CNN model in an end-to-end training manner. We also propose an example of a network with Layer-wise External Attention called Layer-wise External Attention Network (LEA-Net). Through extensive experiments using real-world datasets, we demonstrate that Layer-wise External Attention consistently boosts the anomaly detection performances of an existing CNN model, even on small and unbalanced data. Moreover, we show that Layer-wise External Attention works well with Self-Attention Networks. |
|
言語 |
en |
| 備考 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
3rd International Conference on Image Processing and Vision Engineering, IMPROVE 2023, April 21-23, 2023, Prague, Czech Republic |
|
言語 |
en |
| 書誌情報 |
en : Proceedings of the 3rd International Conference on Image Processing and Vision Engineering IMPROVE
p. 100-110,
発行日 2023
|
| 出版社 |
|
|
出版者 |
SciTePress |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Anomaly Detection |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Visual Inspection AI |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Deep Learning |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Visual Attention Mechanism |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Self-Attention |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
MVTec AD |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Plant Science |
| 言語 |
|
|
言語 |
eng |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_6501 |
|
資源タイプ |
journal article |
| 出版タイプ |
|
|
出版タイプ |
VoR |
|
出版タイプResource |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| DOI |
|
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.5220/0011856800003497 |
| ISSN |
|
|
収録物識別子タイプ |
PISSN |
|
収録物識別子 |
2795-4943 |
| 会議記述 |
|
|
|
会議名 |
3rd International Conference on Image Processing and Vision Engineering, IMPROVE 2023 |
|
|
言語 |
en |
|
回次 |
3 |
|
|
開始年 |
2023 |
|
|
開始月 |
04 |
|
|
開始日 |
21 |
|
|
終了年 |
2023 |
|
|
終了月 |
04 |
|
|
終了日 |
23 |
|
開催国 |
CZE |
| 査読の有無 |
|
|
値 |
yes |
| 連携ID |
|
|
値 |
14114 |
LaSEINE-2023_001.pdf (6.2 MB)
