摘 要：近年来随着深度学习的发展，图像识别与分类问题取得了飞速进展。而在深度学习的研究领域中，卷积神经网络被广泛应用于图像识别。文章对前人在卷积神经网络领域的研究成果进行了梳理与总结。首先介绍了深度学习的发展背景，然后介绍了一些常见卷积网络的模型，并对其中的微网络结构进行简述，最后对卷积神经网络的发展趋势与特点进行分析与总结。在未来的研究中，卷积神经网络仍将作为深度学习的一种重要模型得到进一步发展。
关键词：深度学习；卷积神经网络；微网络
中图分类号：TP301.6 文献标识码：A 文章编号：2096-4706（2021）02-0011-05
Survey of Convolutional Neural Network
MA Shituo1，BAN Yijie1，DAICHEN Zhili2
（1.School of Computer Science and Technology，Huazhong University of Science and Technology，Wuhan 430074，China；2.School of Medical Engineering and Technology，Xinjiang Medical University，Urumqi 830001，China）
Abstract：In recent years，with the development of deep learning，image recognition and classification problems have made rapid progress. In the field of deep learning，convolutional neural network is widely used in image recognition. In this paper，the previous research results in the field of convolutional neural network are combed and summarized. Firstly，it will introduce the development background of deep learning，and then introduce some common convolutional network models，and briefly describes the micro network structure. Finally，it will analyze and summarize the development trend and characteristics of convolutional neural network. In the future research，convolutional neural network will be further developed as an important model of deep learning.
Keywords：deep learning；convolutional neural network；micro network
基金项目：校级大学生创新创业项目（2020A0224）
参考文献：
[1] YANN L C，BENGIO Y，HINTON G. Deep learning [J].Nature，2015，521（7553）：436-444.
[2] RUMELHART D E，HINTON G E，WILLIAMS R J.Learning representations by back-propagating errors [J].Nature，1986，323：533-536.
[3] YANN L C，BOTTOU L，BENGIO Y，et al. Gradient-basedlearning applied to document recognition [J].Proceedings of the IEEE，1998，86（11）：2278-2324.
[4] KRIZHEVSKY A，SUTSKEVER I，HINTON G. ImageNetClassification with Deep Convolutional Neural Networks [C]//NIPS’12.New York：Curran Associates Inc，2012：1-9.
[5] SIMONYAN K，ZISSERMAN A. Very Deep ConvolutionalNetworks for Large-Scale Image Recognition [J/OL].arXiv：1409.1556v6[cs.CV].（2014-04-10）.https://arxiv.org/abs/1409.1556v6.
[6] LIN M，CHEN Q，YAN S C. Network In Network [J/OL].arXiv：1312.4400v3 [cs.NE].（2013-12-16）.https://arxiv.org/abs/1312.4400v3.
[7] S Z E G E D Y C，VA N H O U C K E V，I O F F E S，e t a l .Rethinking the Inception Architecture for Computer Vision [C]//2016IEEE Conference on Computer Vision and Pattern Recognition（CVPR）.Las Vegas：IEEE，2016：2818-2826.
[8] SZEGEDY C，LIU W，JIA Y Q，et al. Going deeper withconvolutions [C]//2015 IEEE Conference on Computer Vision andPattern Recognition（CVPR）.Boston：IEEE，2015：1-9.
[9] HE K M，ZHANG X Y，REN S Q，et al. Deep ResidualLearning for Image Recognition [C]//2016 IEEE Conference on ComputerVision and Pattern Recognition（CVPR）.Las Vegas：IEEE，2016：770-778.
[10] HUANG G，LIU Z，MAATEN L V D，et al. DenselyConnected Convolutional Networks [C]//2017 IEEE Conference onComputer Vision and Pattern Recognition（CVPR）.Honolulu：IEEE，2017：2261-2269.
[11] ZHANG X Y，ZHOU X Y，LIN M X，et al. ShuffleNet：An Extremely Efficient Convolutional Neural Network for MobileDevices [C]//2018 IEEE/CVF Conference on Computer Vision andPattern Recognition.Salt Lake City：IEEE，2018：6848-6856.
[12] HOWARD A G，ZHU M L，CHEN B，et al. MobileNets：Efficient Convolutional Neural Networks for Mobile Vision Applications[J/OL].arXiv：1704.04861v1 [cs.CV].（2017-04-17）.https://arxiv.org/abs/1704.04861v1.
[13] LARSSON G，MAIRE M，SHAKHNAROVICH G.FractalNet：Ultra-Deep Neural Networks without Residuals [J/OL].arXiv：1605.07648v4 [cs.CV].（2017-05-26）.https://arxiv.org/abs/1605.07648v4.
[14] HAN D Y，KIM J H，KIM J M. Deep Pyramidal ResidualNetworks [C]//2017 IEEE Conference on Computer Vision and PatternRecognition（CVPR）.Honolulu：IEEE，2017：6307-6315.
[15] HU J，SHEN L，SUN G. Squeeze-and-Excitation Networks[C]//2018 IEEE/CVF Conference on Computer Vision and PatternRecognition.Salt Lake City：IEEE，2018：7132-7141.
[16] HADJI I，WILDES R P. What Do We Understand AboutConvolutional Networks ？ [J/OL].arXiv：1803.08834v1 [cs.CV].（2018-05-23）.https://arxiv.org/abs/1803.08834.
作者简介：
马世拓（2001.10—）男，汉族，湖北武汉人，本科在读，研究方向：机器学习与数据挖掘；
班一杰（2001.12—），男，汉族，山东临沂人，本科在读，研究方向：物联网工程；
戴陈至力（2002.04—），男，汉族，江苏泰州人，本科在读，研究方向：计算机视觉。