Journal of Frontiers of Computer Science and Technology ›› 2021, Vol. 15 ›› Issue (10): 1795-1811.DOI: 10.3778/j.issn.1673-9418.2103075

• Surveys and Frontiers • Previous Articles     Next Articles

Generative Adversarial Network and Its Research Progress in Image Generation

MA Yongjie, XU Xiaodong, ZHANG Ru, XIE Yirong, CHEN Hong   

  1. School of Physics and Electronic Engineering, Northwest Normal University, Lanzhou 730070, China
  • Online:2021-10-01 Published:2021-09-30

生成式对抗网络及其在图像生成中的研究进展

马永杰徐小冬张茹谢艺蓉陈宏   

  1. 西北师范大学 物理与电子工程学院,兰州 730070

Abstract:

Generative adversarial networks (GAN) has become a popular research direction in the field of deep learning. The unique adversarial idea of GAN comes from the two-player zero-sum game in game theory. How to solve the problems of unstable GAN training, poor quality of generated samples, inadequate evaluation system, poor interpretability and other issues is critical and difficult in current GAN research. This paper investigates the research background and development trend of GAN. First, the basic idea and algorithm implementation of GAN are described, the advantages and disadvantages of GAN are analyzed, a more systematic classification of existing improved methods is made, and some typical optimization methods and derivative models of GAN are sorted out from two categories based on structure change and loss function variants respectively. Next, the similarities and differences between GAN and other generative models are compared, and their respective advantages and disadvantages are introduced. Then, this paper compares the performance of GAN and its derivative models, and summarizes their operation mechanism, advantages, limitations and applicable scenarios. The applications of GAN in the field of image generation are introduced. Finally, the mainstream evaluation indicators of GAN are listed, the main problems still faced in GAN research are analyzed and corresponding solutions are given. The listed mainstream solutions are compared and analyzed in terms of solution effects and applicability, and the future research direction is prospected.

Key words: generative adversarial networks (GAN), machine learning, deep learning, image processing, unsupervised learning, image generation

摘要:

生成式对抗网络(GAN)现已成为深度学习领域热门的研究方向,其独特的对抗性思想来源于博弈论中的二人零和博弈,如何解决GAN训练不稳定、生成样本质量差、评价体系不够健全、可解释性差等问题是目前GAN研究的重点和难点。调研了生成式对抗网络的研究背景和发展趋势。首先阐述了生成式对抗网络的基本思想和算法实现,分析了GAN的优势与不足,然后对已有改进方法进行了较为系统的分类,从基于结构改变和基于损失函数变体的两种类型分别梳理了一些典型的GAN的优化方法和衍生模型;比较了GAN与其他生成模型的异同,介绍了各自的优势与不足;对比了GAN及其衍生模型的性能,总结了它们的运作机制、优点、局限性以及适用场景,介绍了生成式对抗网络在图像生成领域中的应用;最后列举了生成式对抗网络的主流评价指标,分析了GAN研究中仍面临的主要问题并给出对应的解决思路,并将列举出的主流解决手段在解决效果及可应用性方面进行了对比分析,展望了未来的研究方向。

关键词: 生成式对抗网络(GAN), 机器学习, 深度学习, 图像处理, 无监督学习, 图像生成