摘要
生成对抗网络(GANs)是现阶段人工智能的研究热点,介绍了GANs的模型原理,阐述其优点和缺陷及其改进模型,总结了GANs在图像、文字、视频等领域的应用现状和研究进展。
Generating adversarial networks(GANs) is a research hotspot in artificial intelligence at the present stage.This paper introduces the model principle of GANs,expounds its advantages and disadvantages and its improvement model,and summarizes the application status and research of GANs in image,text,video and other fields.
引文
[1]中国信息通信研究院,中国人工智能产业发展联盟.人工智能发展白皮书产业应用篇(2018年)[R/OL].http://www.caict.ac.cn/kxyj/qwfb/bps/201812/P020181227308307634492.pdf
[2]Goodfellow I,Bengio Y,Courville A.Deep Learning[M].Cambridge,UK:MIT Press,2016:104-105
[3]Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[C]∥Advances in neural information processing systems. 2014:2672-2680
[4]MIT Technology Review.10 Breakthrough Technologies 2018.[R/OL].https://www.technologyreview.com/lists/technologies/2018
[5]hindupuravinash.The GAN zoo[R/OL].https://github.com/hindupuravinash/the-gan-zoo
[6]Mirza M,Osindero S. Conditional Generative Adversarial Nets[R/OL][2016-12-22].https://arxiv.org/abs/1411.1784
[7]Zhu W,Miao J,Qing L,et al.Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. Computer Science[R/OL][2014-06-10].https://arxiv.org/abs/1511.06434
[8]Martin Arjovsky,Soumith Chintala,Léon Bottou.Wasserstein GAN[R/OL][2017-01-26]. https://arxiv.org/abs/1701.07875
[9]Agustinus Kristiadi.Least Squares GAN[R/OL] http://wiseodd.github.io/techblog/2017/03/02/least-squares-gan/
[10]David Berthelot,Thomas Schumm,Luke Metz.Boundary Equilibrium Generative Adversarial Networks[R/OL][2017-03-31].https://arxiv.org/abs/1703.10717
[11]Christian Ledig,Lucas Theis,Ferenc Huszar,et al.Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network[R/OL][2016-09-15].https://arxiv.org/abs/1609.04802
[12]Ashish Shrivastava,Tomas Pfister,Oncel Tuzel,et al.Learning from Simulated and Unsupervised Images through Adversarial Training[R/OL][2016-12-22].https://arxiv.org/abs/1612.07828
[13]Scott Reed,Zeynep Akata,Xinchen Yan,et al.Generative Adversarial Text to Image Synthesis[R/OL][2016-05-17].https://arxiv.org/abs/1605.05396
[14]Justin Johnson,Agrim Gupta,Li Fei-Fei.Image Generation from Scene Graphs[R/OL][2018-04-04]. https://arxiv.org/abs/1804.01622
[15]Zeyu Jin, Gautham J. Mysore, Stephen Di Verdi,et al.VoCo:Text-based Insertion and Replacement in Audio Narration.ACM Transactions on Graphics.[R/OL].[2017-7].http://gfx.cs.princeton.edu/pubs/Jin_2017_VTI/
[16]Andrew Brock,Theodore Lim,J.M.Ritchie,Nick Weston.Neural Photo Editing with Introspective Adversarial Networks.[R/OL][2016-09-22]. https://arxiv.org/abs/1609.07093v1
[17]林懿伦,戴星原,李力,等.人工智能研究的新前线:生成式对抗网络[J].自动化学报,2018,44(5):775-792