Conditional Generative Adversarial Networks for Domain Transfer: A Survey

Generative Adversarial Network (GAN), deemed as a powerful deep-learning-based silver bullet for intelligent data generation, has been widely used in multi-disciplines. Furthermore, conditional GAN (CGAN) introduces artificial control information on the basis of GAN, which is more practical for many...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2022-08, Vol.12 (16), p.8350
Main Authors: Zhou, Guoqiang, Fan, Yi, Shi, Jiachen, Lu, Yuyuan, Shen, Jun
Format: Article
Language:English
Subjects:
conditional generative adversarial network
Critical point
cycle consistency
Datasets
Deep learning
domain transfer
Domains
loss function
progressive enhancement mechanism
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Generative Adversarial Network (GAN), deemed as a powerful deep-learning-based silver bullet for intelligent data generation, has been widely used in multi-disciplines. Furthermore, conditional GAN (CGAN) introduces artificial control information on the basis of GAN, which is more practical for many specific fields, though it is mostly used in domain transfer. Researchers have proposed numerous methods to tackle diverse tasks by employing CGAN. It is now a timely and also critical point to review these achievements. We first give a brief introduction to the principle of CGAN, then focus on how to improve it to achieve better performance and how to evaluate such performance across the variants. Afterward, the main applications of CGAN in domain transfer are presented. Finally, as another major contribution, we also list the current problems and challenges of CGAN.
ISSN:2076-3417
2076-3417
DOI:10.3390/app12168350