基于自适应池化的双路卷积神经网络图像分类算法  

Image classification algorithm of dual-channel convolutional neural networks based on adaptive pooling

作　　者：高子翔 张宝华[1] 吕晓琪[1,2] 谷宇 GAO Zi-xiang;ZHANG Bao-hua;LYU Xiao-qi;GU Yu(School of Information Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,China;College of Information Engineering,Inner Mongolia University of Technology,Hohhot 010051,China)

机构地区：[1]内蒙古科技大学信息工程学院,内蒙古包头014010 [2]内蒙古工业大学信息工程学院,内蒙古呼和浩特010051

出　　处：《计算机工程与设计》2019年第5期1334-1338,共5页Computer Engineering and Design

基　　金：国家自然科学基金项目(61663036;61261028);国家海洋局海洋遥测工程技术研究中心创新青年基金项目(2014003);内蒙古自治区高等学校"青年科技英才支持计划"青年科技骨干基金项目(NJYT-14-B11);内蒙古自然科学基金项目(2014MS0610);内蒙古自治区高等学校科学研究基金项目(NJZY145)

摘　　要：针对相同构造的卷积神经网络输入同样的数据集也会提取到不同特征的情况,为利用该差异挖掘图像的深层特征,提出一种双路卷积神经网络模型的图像分类算法。在优化池化组合的基础上,在另一子网络中引入自适应池化丰富差异特征,提高特征表达层次;根据互补测量函数测量子网络间的特征差异的互补性,以此优化损失函数反向传播微调模型权重,提高图像分类的精准度。在MNIST和CIFAR-10图像集上的实验结果表明,基于自适应池化的双路卷积神经网络的分类能力优于现有的深度卷积神经网络。Aiming at the situation that using the convolutional neural network with the same structured convolutional neural network inputting the same data set still extracts different features,to exploit this difference to mine the deep features of the image,a dual-channel convolution neural network model of image classification algorithm was presented.On the basis of optimizing the pooling combination,introducing adaptive pooling into another sub-network to enrich the characteristics of differences and improve the level of feature expression.The complementarity of feature differences was measured between sub-networks according to the complementary measurement function,so as to optimize the loss function,which fine-tuned the model weights by back propagation to improve the accuracy of image classification.Experimental results on the MNIST and CIFAR-10 image sets show that the dual-channel convolutional neural network based on adaptive convolution has better classification ability than the existing deep convolutional neural networks.

关 键 词：图像分类 卷积神经网络 自适应池化 特征互补性 子网络 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]