2022
DOI: 10.1051/shsconf/202213903012
|View full text |Cite
|
Sign up to set email alerts
|

Generative Adversarial Networks: a systematic review and applications

Dimitrios C Asimopoulos,
Maria Nitsiou,
Lazaros Lazaridis
et al.

Abstract: Since their introduction in 2014 Generative Adversarial Networks (GANs) have been employed successfully in many areas such as image processing, computer vision, medical imaging, video as well as other disciplines. A large number of review papers have been published, focusing on certain application areas and proposed methods. In this paper, we collected the most recent review papers, organized the collected information according to the application field and we presented the application areas, the GAN architectu… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
4

Relationship

0
10

Authors

Journals

citations
Cited by 12 publications
(5 citation statements)
references
References 51 publications
0
5
0
Order By: Relevance
“…The most advanced techniques in DGM are variational auto-encoders (VAEs), normalizing flow (NF), and generative adversarial networks (GANs) [53]. Many different architectures are GAN derivatives, including recurrent GAN (RGAN) and recurrent conditional GAN (RCGAN) [54]. Given the recent trend of using GAN approaches to synthesize simulated training sets, we select the time-series generative adversarial network (TimeGAN) [18] as the basis for the data augmentation model based on the characteristics of the sensing dataset.…”
Section: Deep Generative Model Approachesmentioning
confidence: 99%
“…The most advanced techniques in DGM are variational auto-encoders (VAEs), normalizing flow (NF), and generative adversarial networks (GANs) [53]. Many different architectures are GAN derivatives, including recurrent GAN (RGAN) and recurrent conditional GAN (RCGAN) [54]. Given the recent trend of using GAN approaches to synthesize simulated training sets, we select the time-series generative adversarial network (TimeGAN) [18] as the basis for the data augmentation model based on the characteristics of the sensing dataset.…”
Section: Deep Generative Model Approachesmentioning
confidence: 99%
“…In contrast, in our paper the generative model is identified and we aim to estimate its parameters. In computer science, the literature on GAN is rapidly growing; for a recent review see, for example, Cheng, Yang, Tang, Xiong, Zhang, and Lei (2020) or Asimopoulos, Nitsiou, Lazaridis, and Fragulis (2022).…”
Section: Introductionmentioning
confidence: 99%
“…The rise of AI continues to reshape numerous sectors, notably medicine, research, and education [4]. Generative Adversarial Networks (GANs), an innovative subset of AI known for their prowess in image creation and analysis, have shown immense potential [5,6]. These systems harness vast databases and machine learning (ML) algorithms to discern statistical correlations between textual descriptions and corresponding images.…”
Section: Introductionmentioning
confidence: 99%