模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2023, Vol. 36 Issue (3): 252-267    DOI: 10.16451/j.cnki.issn1003-6059.202303005
Researches and Applications Current Issue| Next Issue| Archive| Adv Search |
Double-Branch Multi-attention Mechanism Based Sharpness-Aware Classification Network
JIANG Wentao1, ZHAO Linlin1, TU Chao2
1. School of Software, Liaoning Technical University, Huludao 125105;
2. School of Geomatics, Liaoning Technical University, Fuxin 123032

Download: PDF (3366 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  The key to image classification methods based on convolutional neural networks is to extract distinctive important features. To focus on crucial features and enhance the generalization ability of the model, double-branch multi-attention mechanism based sharpness-aware classification network(DAMSNet) is proposed. Based on the ResNet-34 residual network, the size of the convolutional kernel in the input layer of the network is modified and the max pooling layer is removed to reduce the loss of original image features. Then, the double-branch multi-attention mechanism module is designed and embedded into the residual branch to extract the global and local contextual information in both channel and spatial domains. Additionally, sharpness-aware minimization(SAM) algorithm is introduced and combined with stochastic gradient descent optimizer to simultaneously minimize both loss value and loss sharpness, seeking for neighboring parameters with consistently low loss to enhance the generalization ability of the network. Experiments on CIFAR-10, CIFAR-100 and SVHN datasets demonstrate that DAMSNet achieves high classification accuracy and effectively enhances the generalization ability of the network.
Key wordsImage Classification      Attention Mechanism      Sharpness-Aware Minimization(SAM)      Resi-dual Network     
Received: 10 February 2023     
ZTFLH: TP391  
Fund:National Natural Science Foundation of China(No.61172144), Natural Science Foundation of Liaoning Province(No.20170540426), Key Project of Education Department of Liaoning Province(No.LJYL049)
Corresponding Authors: JIANG Wentao, Ph.D., associate professor. His research interests include image processing, pattern re-cognition and artificial intelligence.   
About author:: ZHAO Linlin, master student. Her research interests include image processing, pattern recognition and artificial intelligence. TU Chao, Ph.D. candidate. His research interests include image processing, pattern recognition and artificial intelligence.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
JIANG Wentao
ZHAO Linlin
TU Chao
Cite this article:   
JIANG Wentao,ZHAO Linlin,TU Chao. Double-Branch Multi-attention Mechanism Based Sharpness-Aware Classification Network[J]. Pattern Recognition and Artificial Intelligence, 2023, 36(3): 252-267.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202303005      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2023/V36/I3/252
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn