Computer Engineering and Applications ›› 2021, Vol. 57 ›› Issue (19): 18-31.DOI: 10.3778/j.issn.1002-8331.2104-0248

Previous Articles     Next Articles

Review of Research on Generative Adversarial Networks and Its Application

WEI Fuqiang, Gulanbaier Tuerhong, Mairidan Wushouer   

  1. School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China
  • Online:2021-10-01 Published:2021-09-29

生成对抗网络及其应用研究综述

魏富强,古兰拜尔·吐尔洪,买日旦·吾守尔   

  1. 新疆大学 信息科学与工程学院,乌鲁木齐 830046

Abstract:

The theoretical research and applications of generative adversarial networks have been continuously successful and have become one of the current hot spots of research in the field of deep learning. This paper provides a systematic review of the theory of generative adversarial networks and their applications in terms of types of models, evaluation criteria and theoretical research progress; analyzing the strengths and weaknesses of generative models with explicit and implicit density-based, respectively; summarizing the evaluation criteria of generative adversarial networks, interpreting the relationship between the criteria, and introduces the research progress of the generative adversarial network in image generation from the application level, that is, through the image conversion, image generation, image restoration, video generation, text generation and image super-resolution applications; analyzing the theoretical research progress of generative adversarial networks from the perspectives of interpretability, controllability, stability and model evaluation methods. Finally, the paper discusses the challenges of studying generative adversarial networks and looks forward to the possible future directions of development.

Key words: generate model, Generative Adversarial Network(GAN), model evaluation, image generation applications

摘要:

生成对抗网络的理论研究与应用不断获得成功,已经成为当前深度学习领域研究的热点之一。对生成对抗网络理论及其应用从模型的类型、评价标准和理论研究进展等方面进行系统的综述:分别分析基于显式密度和基于隐式密度的生成模型的优缺点;总结生成对抗网络的评价标准,解读各标准之间的关系,并从应用层面介绍生成对抗网络在图像及其他领域中的研究进展,即通过图像转换、图像生成、图像修复、视频生成、文本生成及图像超分辨率等的应用;从模型的结构表示、训练控制、性能稳定以及评价标准等角度分析生成对抗网络的理论研究进展。研究讨论生成对抗网络的挑战,展望未来可能存在的发展方向。

关键词: 生成模型, 生成对抗网络, 模型评价, 图像生成应用