Anomaly Detection Using Siamese Network with Attention Mechanism for Few-Shot Learning

Takimoto, Hironori and Seki, Junya and F. Situju, Sulfayanti and Kanagawa, Akihiro (2022) Anomaly Detection Using Siamese Network with Attention Mechanism for Few-Shot Learning. Applied Artificial Intelligence, 36 (1). ISSN 0883-9514

[thumbnail of Anomaly Detection Using Siamese Network with Attention Mechanism for Few Shot Learning.pdf] Text
Anomaly Detection Using Siamese Network with Attention Mechanism for Few Shot Learning.pdf - Published Version

Download (4MB)

Abstract

Automated inspection using deep-learning has been attracting attention for visual inspection at the manufacturing site. However, the inability to obtain sufficient abnormal product data for training deep- learning models is a problem in practical application. This study proposes an anomaly detection method based on the Siamese network with an attention mechanism for a small dataset. Moreover, attention branch loss (ABL) is proposed for Siamese network to render more task-specific attention maps from attention mechanism. Experimental results confirm that the proposed method with the attention mechanism and ABL is effective even with limited abnormal data.

Item Type: Article
Subjects: Souths Book > Computer Science
Depositing User: Unnamed user with email support@southsbook.com
Date Deposited: 17 Jun 2023 09:37
Last Modified: 08 Jun 2024 09:08
URI: http://research.europeanlibrarypress.com/id/eprint/1186

Actions (login required)

View Item
View Item