面向表情识别的重影非对称残差注意力网络模型  

A ghost asymmetric residual attention network model for facial expression recognition

作　　者：闫河 李梦雪 张宇宁 刘建骐 YAN He;LI Mengxue;ZHANG Yuning;LIU Jianqi(School of Artificial Intelligence,Chongqing University of Technology,Chongqing 401135,China)

机构地区：[1]重庆理工大学两江人工智能学院,重庆401135

出　　处：《智能系统学报》2023年第2期333-340,共8页CAAI Transactions on Intelligent Systems

基　　金：国家重点研发计划“智能机器人”重点专项(2018YFB-1308602);国家自然科学基金面上项目(61173184);重庆市自然科学基金项目(cstc2018jcyjAX0694)。

摘　　要：针对ResNet50中的Bottleneck经过1×1卷积降维后主干分支丢失部分特征信息而导致在表情识别中准确率不高的问题,本文通过引入Ghost模块和深度可分离卷积分别替换Bottleneck中的1×1卷积和3×3卷积,保留更多原始特征信息,提升主干分支的特征提取能力;利用Mish激活函数替换Bottleneck中的ReLU激活函数,提高了表情识别的准确率;在此基础上,通过在改进的Bottleneck之间添加非对称残差注意力模块(asymmetric residual attention block, ARABlock)来提升模型对重要信息的表示能力,从而提出一种面向表情识别的重影非对称残差注意力网络(ghost asymmetric residual attention network, GARAN)模型。对比实验结果表明,本文方法在FER2013和CK+表情数据集上具有较高的识别准确率。In this paper,a solution is proposed to address the low accuracy in facial expression recognition that results from the 1×1 convolution dimensionality reduction of the Bottleneck in ResNet50.To do so,the authors introduce the Ghost module and depth separable convolution to replace the 1×1 and 3×3 convolutions in the Bottleneck,respectively,in order to preserve more of the original feature information and improve the feature extraction ability of the trunk branch.The Mish activation function is also used to replace the ReLU activation function in the Bottleneck,further enhancing the accuracy of facial expression recognition.To further improve the ability of the model to express important information,the authors also introduce an asymmetric residual attention block(ARABlock)between the improved Bottlenecks.The proposed method,which is referred to as the ghost asymmetric residual attention network(GARAN)model,shows high recognition accuracy on the FER2013 and CK+facial expression datasets based on comparative experimental results.

关 键 词：表情识别 特征提取 ResNet50 Ghost模块 Mish 非对称残差注意力 深度可分离卷积 深度学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]