自动化学报2016，Vol.42Issue(6)：858-865,8.DOI:10.16383/j.aas.2016.c150658
基于跨连卷积神经网络的性别分类模型
A Gender Classification Model Based on Cross-connected Convolutional Neural Networks
摘要
Abstract
To improve gender classification accuracy, we propose a cross-connected convolutional neural network (CCNN) based on traditional convolutional neural networks (CNN). The proposed model is a 9-layer structure composed of an input layer, six hidden layers (i.e., three convolutional layers alternating with three pooling layers), a fully-connected layer and an output layer, where the second pooling layer is allowed to directly connect to the fully-connected layer across two layers. Experimental results in ten face datasets show that our model can achieve gender classification accuracies not lower than those of the convolutional neural networks.关键词
性别分类/卷积神经网络/跨连卷积神经网络/跨层连接Key words
Gender classification/convolutional neural network (CNN)/cross-connected convolutional neural network (CCNN)/cross-layer connection引用本文复制引用
张婷,李玉鑑,胡海鹤,张亚红..基于跨连卷积神经网络的性别分类模型[J].自动化学报,2016,42(6):858-865,8.基金项目
国家自然科学基金(61175004),高等学校博士学科点专项科研基金(20121103110029),北京市博士后工作资助项目(2015ZZ-24:Q6007011201501)资助Supported by National Natural Science Foundation of China (61175004), Specialized Research Fund for the Doctoral Program of Higher Education of China (20121103110029), and Project Funding of Postdoctor in Beijing (2015ZZ-24：Q6007011201501) （61175004）
