Anomaly Detection Using Siamese Network with Attention Mechanism for Few-Shot Learning
Open Access
- 11 July 2022
- journal article
- research article
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 36 (1)
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.Keywords
This publication has 19 references indexed in Scilit:
- An Unsupervised-Learning-Based Approach for Automated Defect Inspection on Textured SurfacesIEEE Transactions on Instrumentation and Measurement, 2018
- Deep Learning‐Based Crack Damage Detection Using Convolutional Neural NetworksComputer-Aided Civil and Infrastructure Engineering, 2017
- A Generic Deep-Learning-Based Approach for Automated Surface InspectionIEEE Transactions on Cybernetics, 2017
- Design of deep convolutional neural network architectures for automated feature extraction in industrial inspectionCIRP Annals, 2016
- Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction2014
- Convolutional Neural Networks for Steel Surface Defect Detection from Photometric Stereo Images2014
- Steel defect classification with Max-Pooling Convolutional Neural Networks2012
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Learning a Similarity Metric Discriminatively, with Application to Face Verification2005
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998