A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines -- From Medical to Remote Sensing

Dash, Ankan; Ye, Junyi; Wang, Guiling

doi:10.48550/arxiv.2110.01442

Cited by 14 publications

(17 citation statements)

References 152 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generative models refer to a general class of machine learning models which are able to generate things that resemble the input dataset. They have proven to be extremely powerful, and in recent years have found numerous applications such as science, engineering, medicine, art, video games, deepfakes, etc [9]. In most cases GANs performed better than other generative models, such as variational autoencoders, because they are able to learn more hidden rules in the input data set.…”

Section: Introductionmentioning

confidence: 99%

ScGAN: a generative adversarial network to predict hypothetical superconductors

Kim,

Dordevic

2023

J. Phys.: Condens. Matter

View full text Add to dashboard Cite

Despite having been discovered more than three decades ago, high temperature superconductors (HTSs) lack both an explanation for their mechanisms and a systematic way to search for them. To aid this search, this project proposes ScGAN, a generative adversarial network (GAN) to efficiently predict new superconductors. ScGAN was trained on compounds in Open Quantum Materials Database and then transfer learned onto the SuperCon database or a subset of it. Once trained, the GAN was used to predict superconducting candidates, and approximately 70% of them were determined to be superconducting by a classification model–a 23-fold increase in discovery rate compared to manual search methods. Furthermore, more than 99% of predictions were novel materials, demonstrating that ScGAN was able to potentially predict completely new superconductors, including several promising HTS candidates. This project presents a novel, efficient way to search for new superconductors, which may be used in technological applications or provide insight into the unsolved problem of high temperature superconductivity.

show abstract

Section: Introductionmentioning

confidence: 99%

ScGAN: a generative adversarial network to predict hypothetical superconductors

Kim,

Dordevic

2023

J. Phys.: Condens. Matter

View full text Add to dashboard Cite

show abstract

“…An interesting feature about WGANs is that they are less susceptible to mode collapse. They can also be used for a wide range of applications, including audio synthesis, text generation, and image generation, and a wide range of areas of science [62].…”

Section: Generative Adversarial Network (Gans)mentioning

confidence: 99%

A Framework for Demonstrating Practical Quantum Advantage: Racing Quantum against Classical Generative Models

Hibat-Allah¹,

Mauri²,

Carrasquilla³

et al. 2023

Preprint

View full text Add to dashboard Cite

Generative modeling has seen a rising interest in both classical and quantum machine learning, and it represents a promising candidate to obtain a practical quantum advantage in the near term. In this study, we build over the framework proposed in Gili et al. [1] for evaluating the generalization performance of generative models, and we establish the first quantitative comparative race towards practical quantum advantage (PQA) between classical and quantum generative models, namely Quantum Circuit Born Machines (QCBMs), Transformers (TFs), Recurrent Neural Networks (RNNs), Variational Autoencoders (VAEs), and Wasserstein Generative Adversarial Networks (WGANs). After defining four types of PQAs scenarios, we focus on what we refer to as potential PQA, aiming to compare quantum models with the best-known classical algorithms for the task at hand. We let the models race on a well-defined and application-relevant competition setting, where we illustrate and demonstrate our framework on 20 variables (qubits) generative modeling task. Our results suggest that QCBMs are more efficient in the data-limited regime than the other state-of-the-art classical generative models. Such a feature is highly desirable in a wide range of real-world applications where the available data is scarce.

show abstract

“…Ongoing research in this field aims to refine and improve GAN-based content-adaptive metrics, enabling more accurate and context-aware quality assessment in video streaming applications. Cross-Modal Applications: a. Audio-Visual Synchronization [4)]: GAN models employed to synchronize audio and video streams during DASH playback, ensuring lip-sync accuracy and improving the user experience. Audio-visual synchronization is a critical aspect of video streaming to ensure that the audio and video streams are properly aligned, resulting in accurate lip-sync and an improved user experience.…”

Section: Quality Enhancement and Restorationmentioning

confidence: 99%

A Taxonomy for Generative Adversarial Networks in Dynamic Adaptive Streaming Over HTTP

Khan¹

2023

IJMRA

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) have emerged as a powerful tool in the field of Dynamic Adaptive Streaming over HTTP (DASH) to enhance various aspects of video streaming. This paper presents a taxonomy that categorizes the applications and techniques of GANs in the context of DASH. The taxonomy covers several key dimensions, including video generation, compression, quality enhancement, bandwidth adaptation, dynamic bitrate streaming, and cross-modal applications. Within each dimension, specific subcategories are identified to capture the diverse applications of GANs in DASH. Additionally, evaluation metrics for assessing the quality and effectiveness of GAN-based approaches are discussed. The taxonomy serves as a comprehensive framework to understand and organize the different ways in which GANs can be utilized to improve the streaming experience in DASH. By providing an organized structure, this taxonomy facilitates better understanding, comparison, and exploration of GAN-based approaches in DASH and enables researchers and practitioners to identify areas for further research and development.

show abstract

A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines -- From Medical to Remote Sensing

Cited by 14 publications

References 152 publications

ScGAN: a generative adversarial network to predict hypothetical superconductors

ScGAN: a generative adversarial network to predict hypothetical superconductors

A Framework for Demonstrating Practical Quantum Advantage: Racing Quantum against Classical Generative Models

A Taxonomy for Generative Adversarial Networks in Dynamic Adaptive Streaming Over HTTP

Contact Info

Product

Resources

About