More Key Applications of GANs

Xudong Mao () and Qing Li ()
Additional contact information
Xudong Mao: Hong Kong Polytechnic University, Department of Computing
Qing Li: Hong Kong Polytechnic University, Department of Computing

Chapter Chapter 3 in Generative Adversarial Networks for Image Generation, 2021, pp 53-74 from Springer

Abstract: Abstract In the previous chapter, we learned that GANs are very powerful for image generation. In this chapter, we learn three interesting applications of GANs: image-to-image translation, unsupervised domain adaptation, and GANs for security. One type of GANs application is for tasks that require high-quality images, such as image-to-image translation. To improve the output image quality, a discriminator is introduced to judge whether the output images are realistic. Another type is to extend the use of the discriminator in a more generalized way, such as unsupervised domain adaptation. For instance, the task of unsupervised domain adaptation includes two domain datasets, the source domain and the target domain. To learn indistinguishable feature representations for the source and target domains, we can introduce a discriminator to judge whether the output features come from the source domain or the target domain.

Date: 2021
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-981-33-6048-8_3

Ordering information: This item can be ordered from
http://www.springer.com/9789813360488

DOI: 10.1007/978-981-33-6048-8_3

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().