Generative adversarial networks (GANs): Introduction, Taxonomy, Variants, Limitations, and Applications

• Published in: Multimedia tools and applications Vol. 83; no. 41; pp. 88811 - 88858
• Main Authors: Sharma, Preeti, Kumar, Manoj, Sharma, Hitesh Kumar, Biju, Soly Mathew
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.12.2024; Springer Nature B.V
• Subjects: Computer Communication Networks; Computer Science; Data Structures and Information Theory; Deep learning; Deepfake; Demand analysis; Effectiveness; Forensic sciences; Generative adversarial networks; Multimedia; Multimedia Information Systems; Neural networks; Special Purpose and Application-Based Systems; Taxonomy; Visual fields; Deep learning; Image vision; Deep fakes; GAN variants; GAN architecture; Digital forensics; Generative adversarial network; GAN models; Deep learning based methods
• DOI: 10.1007/s11042-024-18767-y
• ISSN: 1573-7721; 1380-7501

The growing demand for applications based on Generative Adversarial Networks (GANs) has prompted substantial study and analysis in a variety of fields. GAN models have applications in NLP, architectural design, text-to-image, image-to-image, 3D object production, audio-to-image, and prediction. This technique is an important tool for both production and prediction, notably in identifying falsely created pictures, particularly in the context of face forgeries, to ensure visual integrity and security. GANs are critical in determining visual credibility in social media by identifying and assessing forgeries. As the field progresses, a variety of GAN variations arise, along with the development of diverse assessment techniques for assessing model efficacy and scope. The article provides a complete and exhaustive overview of the most recent advances in GAN model designs, the efficacy and breadth of GAN variations, GAN limits and potential solutions, and the blooming ecosystem of upcoming GAN tool domains. Additionally, it investigates key measures like as Inception Score (IS) and Fréchet Inception Distance (FID) as critical benchmarks for improving GAN performance in contrast to existing approaches.