| 基于跨连卷积神经网络的性别分类模型 |
| |
| 引用本文： | 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. 自动化学报, 2016, 42(6): 858-865. doi: 10.16383/j.aas.2016.c150658 |
| |
| 作者姓名： | 张婷 李玉鑑 胡海鹤 张亚红 |
| |
| 作者单位： | 北京工业大学计算机学院 北京 100124 |
| |
| 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 |
| |
| 摘 要： | 为提高性别分类准确率, 在传统卷积神经网络(Convolutional neural network, CNN)的基础上, 提出一个跨连卷积神经网络(Cross-connected CNN, CCNN)模型. 该模型是一个9层的网络结构, 包含输入层、6个由卷积层和池化层交错构成的隐含层、全连接层和输出层, 其中允许第2个池化层跨过两个层直接与全连接层相连接. 在10个人脸数据集上的性别分类实验结果表明, 跨连卷积网络的准确率均不低于传统卷积网络.
|
| 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 |
| 收稿时间： | 2015-10-16 |
A Gender Classification Model Based on Cross-connected Convolutional Neural Networks |
| |
| ZHANG Ting, LI Yu-Jian, HU Hai-He, ZHANG Ya-Hong. A Gender Classification Model Based on Cross-connected Convolutional Neural Networks. ACTA AUTOMATICA SINICA, 2016, 42(6): 858-865. doi: 10.16383/j.aas.2016.c150658 |
| |
| Authors: | ZHANG Ting LI Yu-Jian HU Hai-He ZHANG Ya-Hong |
| |
| Affiliation: | Computer School, Beijing University of Technology, Beijing 100124 |
| |
| 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. |
| |
| Keywords: | Gender classification convolutional neural network (CNN) cross-connected convolutional neural network (CCNN) cross-layer connection |
|
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
|
