生成对抗网络在计算机视觉领域的应用
The Applications of Generative Adversarial Networks in the Field of Computer Vision
摘要: 生成对抗网络(GAN, Generative Adversarial Networks)的出现是计算机视觉领域又一里程碑式的发展，它为解决各种图像预测问题提供了新型工具。以此为目的，本文通过相关文献的调研以及结合最新成果的研究，突出了生成对抗网络的无监督学习算法特征。目前生成对抗网络拓扑结构的研究在不断优化着基础生成对抗网络的性能；在改进难收敛、模式崩溃等缺点方面发挥着各自的长处，已然成为当下研究的热点方向之一。
Abstract: The emergence of generative adversarial networks is another milestone in the field of computer vision. It provides a new tool for solving various image prediction problems. For this purpose, from the investigation of relevant literatures and latest research results, the characteristics of unsupervised learning algorithms are highlighted. At present, the topology of the generative adversarial networks is continuously optimized to its basic performance. It has become one of the hot topics of current research to play their respective strengths in improving the difficulties such as non-convergence, mode collapse and so on.
文章引用：江春雨, 程琳, 黎晓明亮. 生成对抗网络在计算机视觉领域的应用[J]. 计算机科学与应用, 2018, 8(11): 1726-1733. https://doi.org/10.12677/CSA.2018.811191

参考文献

[1] Halbritter, S. (2016) Generative Adversarial Networks. Hamburg University of Applied Science, Hamburg.
[2] Goodfellow, I. (2016) Nips2016 Tutorial: Generative Adversarial Networks. arXiv preprint arXiv:1701.00160.
[3] Goodfellow, I., Pou-get-Abadie, J. and Mirza, M. (2014) Generative Adversarial Net. NIPS 2014: Advances in Neural Information Processing Sys-tems, 27, 2672-2680.
[4] Cun, Y.L., Bengio, Y. and Hinton, G. (2015) Deep Learning. Nature, 521, 436-444.
[5] Kotsiantis, S.B. (2007) Supervised Machine Learning: A Review of Classification Techniques. Informatica, 31, 249-268.
[6] Goodfellow, I. and Bengio, Y. 深度学习[M]. 北京: 人民邮电出版社, 2017.
[7] 殷瑞刚, 魏帅, 李晗, 于洪. 深度学习中的无监督学习方法综述[J]. 计算机系统应用, 2016, 25(8): 1-7.
[8] 孙吉贵, 刘杰, 赵连宇. 聚类算法研究[J]. 软件学报, 2008, 19(1): 48-61.
[9] 李彦冬, 郝宗波, 雷航. 卷积神经网络研究综述[J]. 计算机应用, 2016, 36(9): 2508-2515.
[10] 百度百科.生成模型. 2018.
https://baike.baidu.com/item/%E7%94%9F%E6%88%90%E6%A8%A1%E5%9E%8B/6563656
[11] Ratliff, L.J., Bur-den, S.A. and Sastry, S.S. (2013) Characterization and Computation of Local Nash Equilibria in Continuous Games. In: Pro-ceedings of the 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton), Monticello, IL, 2-4 October 2013, 917-924. [Google Scholar] [CrossRef] 
[12] Mirza, M. and Osindero, S. (2014) Condi-tional Generative Adversarial Nets. arXiv preprint arXiv: 1411.1784.
[13] 黄锦池. 条件对抗网络. 2018.
https://blog.csdn.net/hjimce/article/details/54407981
[14] Isola, P., Zhu, J.-Y., Zhou, T.H. and Efros, A.A. (2017) Im-age-to-Image Translation with Conditional Adversarial Networks. Conference on Computer Vision and Pattern Recogni-tion.
[15] Radford, A. and Metz, L. (2016) Unsupervised Representation Learning with Deep Convolutional Generative Ad-versarial Networks.
https://arxiv.org/pdf/15-11.06434.pdf
[16] Zhu, J.-Y., Park, T., Isola, P. and Efros, A.A. (2017) Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. CoRR,abs/1703.10593.