摘要
在图像分类任务中,为了获得更高的分类精度,需要对图像提取不同层次的特征信息.深度学习被越来越多地应用于大规模图像分类任务中.提出了一种基于深度卷积神经网络的、可应用于大规模图像分类的深度学习框架.该框架在经典的深度卷积神经网络AlexNet基础上,分别从网络框架和网络内部结构两个方面对网络进行了优化和改进,进一步提升了网络的特征表达能力.同时,通过在全连接层引入隐层,使得网络能够同时具备学习图像特征和二值哈希的功能,从而使该框架具有处理大规模图像数据的能力.通过在3个标准数据库中的一系列比对实验,分析了不同优化方法在不同情况下的作用,并证明了所提优化方法的有效性.
Features from different levels should be extracted from images for more accurate image classification.Deep learning is used more and more in large scale image classification.This paper proposes a deep learning framework based on deep convolutional neural network that can be applied for the large scale image classification.The proposed framework has modified the framework and the internal structure of the classical deep convolutional neural network AlexNet to improve the feature representation ability of the network.Furthermore,this framework has the ability of learning image features and binary hash simultaneously by introducing the hidden layer in the full-connection layer.The proposal has been validated in showing significance improvement through the serial experiments in three commonly used databases.Lastly,different effects of different optimization methods are analyzed.
作者
白琮
黄玲
陈佳楠
潘翔
陈胜勇
BAI Cong;HUANG Ling;CHEN Jia-Nan;PAN Xiang;CHEN Sheng-Yong(College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China)
出处
《软件学报》
EI
CSCD
北大核心
2018年第4期1029-1038,共10页
Journal of Software
基金
国家自然科学基金(61502424
U1509207
61325019)
浙江省自然科学基金(LY15F020028
LY15F020024
LY18F020032)~~
关键词
图像分类
哈希编码
深度卷积神经网络
激活函数
池化
image classification
hash coding
deep conventional neural network
activation function
pooling