###
:2019,28(11):1-9
本文二维码信息
码上扫一扫!
生成对抗网络研究综述
(华南师范大学 计算机学院, 广州 510631)
Review on Generative Adversarial Network
(School of Computer Science, South China Normal University, Guangzhou 510631, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 59次   下载 29
投稿时间:2019-04-17    修订日期:2019-05-16
中文摘要: 自生成对抗网络GAN提出以后,现这一方向已成为人工智能方向的研究热点.GAN的思想采用二人零和博弈方法,由生成器和判别器构成,生成器负责生成样本分布,判别器则判别输入是真实样本还是生成样本,生成器和判别器不断交互优化,最终达到最优效果.GAN模型的提出无疑是很新颖的,但也存在很多缺点,比如梯度消失问题、模式崩溃等.随着研究的深入,GAN不断优化扩展,GAN的衍生模型也层出不穷.GAN可应用于不同领域,主要为计算机图像和视觉领域,在图像领域有着突出的效果,能生成高分辨率逼真的图像,能对图像进行修复、风格迁移等,也能生成视频并进行预测等.GAN也能生成文本,可以进行对话生成、机器翻译、语音生成等.同时,GAN在其他领域也有涉及,比如生成音乐、密码破译等.但是GAN在其他领域的应用效果并不显著,那么,如何提高GAN在其他领域的应用效果将值得深入研究,使生成对抗网络在人工智能方面大放异彩.
Abstract:Since the proposal of generative adversarial networks, GAN has become a research hotspot of artificial intelligence. GAN adopts the method of the zero-sum game between two people, which consists of a generator and a discriminator. The generator is responsible for generating the sample distribution, and the discriminator is responsible for determining whether the input is a real sample or a generated sample. The generator and discriminator constantly interact and optimize to achieve the optimal effect. The model of GAN is undoubtedly very novel, but there are also many shortcomings, such as the problem of gradient disappearance, collapse mode, and so on. With the deepening of research, GAN has been continuously optimized and expanded, and the derivative models of GAN have emerged in endlessly. GAN has been optimized and improved. Also, GAN can be applied in different fields, though it is mainly used in the field of computer image and vision. It has outstanding effects in the field of image. It can generate high-resolution realistic images, repair images, transfer styles, and generate video and prediction. GAN can also generate text, to do some work, such as dialogue generation, machine translation, voice generation, and so on. GAN is also involved in other fields, such as generating music and decoding codes. However, the application effect of GAN in other fields is not significant. Therefore, how to improve its application effect is worthy of further study, which will make the generation of confrontation networks shine in artificial intelligence.
文章编号:     中图分类号:    文献标志码:
基金项目:国家社会科学基金重大项目(14ZDB101);国家自然科学基金(61105133)
引用文本:
邹秀芳,朱定局.生成对抗网络研究综述.计算机系统应用,2019,28(11):1-9
ZOU Xiu-Fang,ZHU Ding-Ju.Review on Generative Adversarial Network.COMPUTER SYSTEMS APPLICATIONS,2019,28(11):1-9

用微信扫一扫

用微信扫一扫