摘要
近年来,深度学习在计算机视觉、语音识别、自然语言处理和医疗影像处理等领域取得了一系列显著的研究成果。在不同类型的深度神经网络中,卷积神经网络得到了最广泛的研究,这不仅体现在学术研究领域的繁荣,更体现在对相关产业产生了巨大的现实影响和商业价值上。随着标注样本数据集的快速增长和图形处理器(GPU)性能的大幅度提高,卷积神经网络的相关研究得到了迅速的发展,并在计算机视觉领域的各种任务中成效卓然。首先,回顾了卷积神经网络的发展历史;其次,介绍了卷积神经网络的基本结构及各组件的作用;然后,详细描述了卷积神经网络在卷积层、池化层和激活函数等方面的改进研究,总结了自1998年以来比较有代表性的神经网络架构:AlexNet,ZF-Net,VGGNet,GoogLeNet,ResNet,DenseNet,DPN和SENet;在计算机视觉领域,重点介绍了卷积神经网络在图像分类/定位、目标检测、目标分割、目标跟踪、行为识别和图像超分辨率重构等应用方面的最新研究进展;最后,对卷积神经网络研究中亟待解决的问题与挑战进行了总结。
In recent years,deep learning has achieved a series of remarkable research results in various fields such as computer vision,speech recognition,natural language processing and medical image processing.In different types of deep neural networks,convolution neural network has obtained most extensive study,not only reflecting the prosperity in aca- demic field,but also making a tremendous realistic impact and commercial value on the related industries.With the rapid growth of annotation sample data sets and the drastic improvement of GPU performance,related researches on convolutional neural networks are rapidly developed and have achieved remarkable results in various tasks in the field of computer vision.This paper reviewed the history of convolution neural network firstly.Then it introduced the basic structure of convolutional neural network and the function of each component.Next,it described the improvements of convolution neural network in convolution layer,pooling layer and activation function in detail.Also,it summarized typical neural network architectures since 1998(such as AlexNet,ZF-Net,VGGNet,GoogLeNet,ResNet,DenseNet,DPN and SENet).In the field of computer vision,this paper emphatically introduced the latest research progresses of convolution neural network in image classification / localization,target detection,target segmentation,target tracking,behavior re- cognition and image super-resolution reconstruction.Finally,it summarized the problems and challenges to be solved about convolutional neural network.
作者
陈超
齐峰
CHEN Chao;QI Feng(School of Management Science and Engineering,Shandong Normal University,Jinan 250000,China)
出处
《计算机科学》
CSCD
北大核心
2019年第3期63-73,共11页
Computer Science
基金
国家自然科学基金项目(61502283
61472231
61640201)资助
关键词
人工智能
深度学习
卷积神经网络
计算机视觉
Artificial intelligence
Deep learning
Convolution neural network
Computer vision
