图像分类的深度卷积神经网络模型综述  

Overview of deep convolutional neural networks for image classification

作　　者：张珂[1,2] 冯晓晗 郭玉荣 苏昱坤 赵凯[1] 赵振兵[1] 马占宇[2] 丁巧林[1] Zhang Ke;Feng Xiaohan;Guo Yurong;Su Yukun;Zhao Kai;Zhao Zhenbing;Ma Zhanyu;Ding Qiaolin(Department of Electronic and Communication Engineering,North China Electric Power University,Baoding 071000,China;Institute of Artificial Intelligence,Beijing University of Posts and Telecommunication,Beijing 100086,China)

机构地区：[1]华北电力大学电子与通信工程系,保定071000 [2]北京邮电大学人工智能学院,北京100086

出　　处：《中国图象图形学报》2021年第10期2305-2325,共21页Journal of Image and Graphics

基　　金：国家自然科学基金项目(62076093,61871182,61922015,61773071,61302163);河北省自然科学基金项目(F2020502009,F2015502062,F2016502062);北京市自然科学基金项目(4192055);中央高校基本科研业务费专项资金资助(2020YJ006,2020MS099)。

摘　　要：图像分类是计算机视觉中的一项重要任务,传统的图像分类方法具有一定的局限性。随着人工智能技术的发展,深度学习技术越来越成熟,利用深度卷积神经网络对图像进行分类成为研究热点,图像分类的深度卷积神经网络结构越来越多样,其性能远远好于传统的图像分类方法。本文立足于图像分类的深度卷积神经网络模型结构,根据模型发展和模型优化的历程,将深度卷积神经网络分为经典深度卷积神经网络模型、注意力机制深度卷积神经网络模型、轻量级深度卷积神经网络模型和神经网络架构搜索模型等4类,并对各类深度卷积神经网络模型结构的构造方法和特点进行了全面综述,对各类分类模型的性能进行了对比与分析。虽然深度卷积神经网络模型的结构设计越来越精妙,模型优化的方法越来越强大,图像分类准确率在不断刷新的同时,模型的参数量也在逐渐降低,训练和推理速度不断加快。然而深度卷积神经网络模型仍有一定的局限性,本文给出了存在的问题和未来可能的研究方向,即深度卷积神经网络模型主要以有监督学习方式进行图像分类,受到数据集质量和规模的限制,无监督式学习和半监督学习方式的深度卷积神经网络模型将是未来的重点研究方向之一;深度卷积神经网络模型的速度和资源消耗仍不尽人意,应用于移动式设备具有一定的挑战性;模型的优化方法以及衡量模型优劣的度量方法有待深入研究;人工设计深度卷积神经网络结构耗时耗力,神经架构搜索方法将是未来深度卷积神经网络模型设计的发展方向。Image classification(IC)is one of important tasks in support of computer vision.Traditional image classification methods have limitations on the aspect of computer vision.Deep learning technology has become more mature than before based on deep convolutional neural network(DCNN)with the development of artificial intelligence(AI)recently.The performance of image classification has been upgraded based on the maturation of the deep convolutional neural network model.This research has mainly focused on a comprehensive overview of image classification in DCNN via the deep convolutional neural network model structure of image classification.Firstly,the modeling methodology has been analyzed and summarized.The DCNN analysis has been formulated into four categories listed below:1)classic deep convolutional neural networks;2)deep convolutional neural networks based on the attention mechanism;3)lightweight networks;4)the neural architecture search method.DCNN has high optimization capability using convolution to extract effective features of the images and learn feature expression from a large number of samples automatically.DCNN achieves better performance on image classification due to the effective features based on the deeper DCNN research and development.DCNN has been encounting lots of difficulities such as overfitting,vanishing gradient and huge model parameters.Hence,DCNN has become more and more difficult to optimize.The researchers in the context of IC have illustrated different DCNN models for different problems.Researchers have been making the network deeper that before via Alex Net.Subsequently,the classified analyses such as network in network(NIN),Overfeat,ZFNet,Visual Geometry Group(VGGNet),Goog Le Net have been persisted on.The problem of vanishing gradient has been more intensified via the deepening of the network.The optimization of the network becomes more complicated.Researchers have proposed residual network(ResNet)to ease gradient vanishing to improve the performance of image classification greatly.T

关 键 词：深度学习 图像分类(IC) 深度卷积神经网络(DCNN) 模型结构 模型优化 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]