《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (6): 1826-1832.DOI: 10.11772/j.issn.1001-9081.2022071008

• 人工智能 • 上一篇    下一篇

基于注意力机制和迁移学习的古壁画朝代识别

张慧斌1,2(), 冯丽萍1, 郝耀军1, 王一宁1   

  1. 1.忻州师范学院 计算机系,山西 忻州 034000
    2.燕山大学 信息科学与工程学院,河北 秦皇岛 066004
  • 收稿日期:2022-07-11 修回日期:2022-11-18 接受日期:2022-11-30 发布日期:2023-01-04 出版日期:2023-06-10
  • 通讯作者: 张慧斌
  • 作者简介:张慧斌(1971—),男,山西忻州人,副教授,博士研究生,主要研究方向:深度学习、应用数学Email:927433441@qq.com
    冯丽萍(1976—),女,山西忻州人,教授,博士,主要研究方向:分布式优化、深度学习
    郝耀军(1979—),男,山西忻州人,教授,博士,主要研究方向:深度学习、推荐系统的信息安全
    王一宁(1992—),女,山西长治人,助教,硕士,主要研究方向:深度学习、人工智能。
  • 基金资助:
    教育部人文社科青年基金资助项目(20YJC630034);山西省自然科学基金资助项目(20210302124330);山西省回国留学人员科研资助项目(2020-139)

Ancient mural dynasty identification based on attention mechanism and transfer learning

Huibin ZHANG1,2(), Liping FENG1, Yaojun HAO1, Yining WANG1   

  1. 1.Department of Computer,Xinzhou Normal University,Xinzhou Shanxi 034000,China
    2.School of Information Science and Engineering,Yanshan University,Qinhuangdao Hebei 066004,China
  • Received:2022-07-11 Revised:2022-11-18 Accepted:2022-11-30 Online:2023-01-04 Published:2023-06-10
  • Contact: Huibin ZHANG
  • About author:FENG Liping, born in 1976, Ph. D., professor. Her research interests include distributed optimization, deep learning.
    HAO Yaojun, born in 1979, Ph. D., professor. His research interests include deep learning, information security of recommendation system.
    WANG Yining, born in 1992, M. S., teaching assistant. Her research interests include deep learning, artificial intelligence.
  • Supported by:
    Youth Foundation of Humanities and Social Sciences Research of Ministry of Education(20YJC630034);Natural Science Foundation of Shanxi Province(20210302124330);Research Project Supported by Shanxi Scholarship Council of China(2020-139)

摘要:

卷积神经网络(CNN)已成功用于敦煌古壁画的朝代分类。针对敦煌壁画的数据量有限,采用某些数据增强方法对训练集进行扩充时反而会降低预测准确率的问题,提出了一种基于注意力机制和迁移学习的残差网络(ResNet)模型。首先,改进了残差网络的残差连接方式;然后,使用极化自注意力(POSA)模块帮助网络模型提取图像的边缘局部细节特征和全局轮廓特征,增强网络模型在小样本环境下的学习能力;最后,改进分类器的算法,提高网络模型的分类性能。实验结果表明,所提模型在敦煌壁画DH1926小样本数据集上,取得了98.05%的朝代分类准确率,与标准的ResNet20网络模型相比,所提模型的朝代识别准确率提高了5.21个百分点。

关键词: 卷积神经网络, 注意力机制, 迁移学习, 残差网络, 古壁画朝代识别

Abstract:

Convolutional Neural Networks (CNNs) have been successfully used to classify dynasties of ancient murals from Dunhuang. Aiming at the problem that using some data enhancement methods to expand the training set would reduce the prediction accuracy due to the limited amount of data of Dunhuang murals, a Residual Network (ResNet) model based on attention mechanism and transfer learning was proposed. Firstly, the residual connection method of the residual network was improved. Then, the POlarized Self-Attention (POSA) module was used to help the network model to extract the edge local detail features and global contour features of the images, and the learning ability of the network model in a small sample environment was enhanced. Finally, the algorithm for classifier was improved, so that the classification performance of the network model was improved. Experimental results show that the proposed model achieves 98.05% accuracy of dynastic classification on DH1926 small sample dataset of Dunhuang murals, and the dynasty identification accuracy of the proposed model is improved by 5.21 percentage points compared with that of the standard ResNet20 network model.

Key words: Convolutional Neural Network (CNN), attention mechanism, transfer learning, Residual Network (ResNet), ancient mural dynasty identification

中图分类号: