计算机工程与应用2019，Vol.55Issue(8)：9-16,8.DOI:10.3778/j.issn.1002-8331.1812-0047
基于注意力卷积模块的深度神经网络图像识别
Deep Neural Network Based on Attention Convolution Module for Image Recognition
摘要
Abstract
For deep fusion in the middle layer branches of deep neural networks, it is a challenge for recent deep neural network research to generate a basic network that can share useful information, thereby optimizing information flow and improving the performance of deep neural networks. In this paper, the deep neural network based on attention convolution module is proposed. The proposed module is mainly divided into two parts:the trunk branch and the soft branch. On the trunk branch, it consists of two sets of residual modules, making the module suitable for other deep neural networks. On the soft branch, the given intermediate feature map is taken along two dimensions(space and channel)to obtain the attention feature map, and the input intermediate feature map is adjusted to strengthen useful information to suppress useless informa-tion. The proposed convolution residual module can solve the problem of inconsistent input and output size, strengthen the key information of the image and effectively promote the information flow of the network. Experiments on the cifar-10, cifar-100, ck+, AVEC2017 data sets show that the proposed method applied to the resnet-50 network has a higher rec-ognition accuracy(0.9%~1.2%)than the method proposed by Hu when the training time difference is less than 0.3%.关键词
图像识别/残差模块/注意力/深度神经网络Key words
image identification/ residual module/ attention/ deep neural network分类
信息技术与安全科学引用本文复制引用
袁嘉杰,张灵,陈云华..基于注意力卷积模块的深度神经网络图像识别[J].计算机工程与应用,2019,55(8):9-16,8.基金项目
国家重点研发计划项目(No.2016YFB1000605) （No.2016YFB1000605）
国家自然科学基金(No.11575223). （No.11575223）
