Abstract
Generative adversarial networks (GANs) present a way to learn deep representations without extensively annotated training data. These networks achieve learning through deriving back propagation signals through a competitive process involving a pair of networks. The representations that can be learned by GANs may be used in several applications. GANs have made significant advancements and tremendous performance in numerous applications. The essential applications include semantic image editing, style transfer, image synthesis, image super-resolution and classification. This paper aims to present an overview of GANs, its different variants, and potential application in various domains. The paper attempts to identify GANs' advantages, disadvantages and significant challenges to the successful implementation of GAN in different application areas. The main intention of this paper is to explore and present a comprehensive review of the crucial applications of GANs covering a variety of areas, study of the techniques and architectures used and further the contribution of that respective application in the real world. Finally, the paper ends with the conclusion and future aspects.