图像分类卷积神经网络的特征选择模型压缩方法（英文）  

Convolutional neural networks model compression based on feature selection for image classification

作　　者：邹月娴[1] 余嘉胜 陈泽晗 陈锦 王毅 ZOU Yue-xian;YU Jia-sheng;CHEN Ze-han;CHEN Jin;WANG Yi(ADSPLAB/ELIP, School of Electronic and Computer Engineering, Peking University, Shenzhen Guangdong 518055, China)

机构地区：[1]北京大学信息工程学院现代信号与数据处理实验室,广东深圳518055

出　　处：《控制理论与应用》2017年第6期746-752,共7页Control Theory & Applications

基　　金：Supported by Shenzhen Science&Technology Fundamental Research Program(JCYJ20150430162332418)

摘　　要：深度卷积神经网络(convolutional neural networks,CNN)作为特征提取器(feature extractor,CNN-FE)已被广泛应用于许多领域并获得显著成功.根据研究评测可知CNN-FE具有大量参数,这大大限制了CNN-FE在如智能手机这样的内存有限的设备上的应用.本文以AlexNet卷积神经网络特征提取器为研究对象,面向图像分类问题,在保持图像分类性能几乎不变的情况下减少CNN-FE模型参数量.通过对AlexNet各层参数分布的详细分析,作者发现其全连接层包含了大约99%的模型参数,在图像分类类别较少的情况,AlexNet提取的特征存在冗余.因此,将CNN-FE模型压缩问题转化为深度特征选择问题,联合考虑分类准确率和压缩率,本文提出了一种新的基于互信息量的特征选择方法,实现CNN-FE模型压缩.在公开场景分类数据库以及自建的无线胶囊内窥镜(wireless capsule endoscope,WCE)气泡图片数据库上进行图像分类实验.结果表明本文提出的CNN-FE模型压缩方法减少了约83%的AlexNet模型参数且其分类准确率几乎保持不变.Deep convolutional neural networks(CNN)feature extractor(CNN--FE)has been widely applied in many applications and achieved great success.However,evaluating shows that the CNN--FE holds abundant parameters which largely limits its applications on memory-limited platforms,such as smartphones.This study makes an effort to trim the well-known CNN--FEs,AlexNet,to reduce its parameters meanwhile the image classification performance almost remains unchanged.This task is considered as a CNN--FE model compression problem.Through carefully analyzing the parameter distribution of AlexNet,we find about99%of parameters are in its fully connected layer but the deep features are redundant for image classification tasks with small number of categories.Moreover,we propose to convert the CNN-FE model compression problem into a feature selection problem.Specifically,a feature selection method,which is based on mutual information and a novel criterion related to the classification accuracy and the compression ratio,has been proposed.Image classification experiments on a public scene categories database and our self-built wireless capsule endoscope(WCE)bubble dataset show that our proposed CNN--FE model compression method reduces more than83%size of the AlexNet while almost maintaining the classification accuracy.

关 键 词：卷积神经网络 图像分类 特征提取 特征选择 模型压缩 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]