Review and Prospect of Research on Generative Adversarial Networks

被引:0
作者
Fan, Zhao [1 ]
Hu, Jin [1 ]
机构
[1] Natl Univ Def Technol, Elect Countermeasure Inst, Hefei, Peoples R China
来源
2019 IEEE 11TH INTERNATIONAL CONFERENCE ON COMMUNICATION SOFTWARE AND NETWORKS (ICCSN 2019) | 2019年
关键词
generative adversarial networks (GAN); deep learning; neural networks;
D O I
10.1109/iccsn.2019.8905263
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Since it was proposed in 2014, generative adversarial networks (GAN) has been highly concerned and widely studied by industrial circles and artificial intelligence researchers. It provides a new idea for the construction of the generative model. This paper reviews the research progress of GAN and prospects its development trend. Section 2 describes the basic idea and model structure of GAN. Section 3 introduces several typical derivative models of GAN. Section 4 lists GAN's applications in many fields, such as image, vision, voice, language, and etc. Section 5 makes a forward look and thinks on the development trend of GAN, and discusses the application of GAN in the field of communication countermeasures. Finally, section 6 summarizes this paper.
引用
收藏
页码:726 / 730
页数:5
相关论文
共 28 条
[1]  
Arjovsky M, 2017, PR MACH LEARN RES, V70
[2]  
Chen X, 2016, ADV NEURAL INFORM PR, P2172
[3]  
Denton E. L., 2015, Deep Generative Image Models using a obj Laplacian Pyramid of Adversarial Networks, P1486
[4]  
Goodfellow I., 2016, Nips 2016 tutorial: Generative adversarial networks
[5]  
Goodfellow IJ, 2014, ADV NEUR IN, V27, P2672
[6]  
Hu W., 2017, Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
[7]   Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis [J].
Huang, Rui ;
Zhang, Shu ;
Li, Tianyu ;
He, Ran .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :2458-2467
[8]  
Kusner M. J., 2016, ARXIV161104051
[9]   Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network [J].
Ledig, Christian ;
Theis, Lucas ;
Huszar, Ferenc ;
Caballero, Jose ;
Cunningham, Andrew ;
Acosta, Alejandro ;
Aitken, Andrew ;
Tejani, Alykhan ;
Totz, Johannes ;
Wang, Zehan ;
Shi, Wenzhe .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :105-114
[10]  
Li J, 2017, P C EMP METH NAT LAN, P2157, DOI [DOI 10.1021/ACSANM.8B01974, 10.18653/V1/D17-1230]