基于注意力机制和迁移学习的古壁画朝代识别  

Ancient mural dynasty identification based on attention mechanism and transfer learning

作　　者：张慧斌[1,2] 冯丽萍 郝耀军[1] 王一宁[1] ZHANG Huibin;FENG Liping;HAO Yaojun;WANG Yining(Department of Computer,Xinzhou Normal University,Xinzhou Shanxi 034000,China;School of Information Science and Engineering,Yanshan University,Qinhuangdao Hebei 066004,China)

机构地区：[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

出　　处：《计算机应用》2023年第6期1826-1832,共7页journal of Computer Applications

基　　金：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)。

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。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.

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 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]