A Review of Generative Adversarial Networks (GANs) and Its Applications in a Wide Variety of Disciplines: From Medical to Remote Sensing

Abstract

We look into Generative Adversarial Network (GAN), its prevalent variants and applications in a number of sectors. GANs combine two neural networks that compete against one another using zerosum game theory, allowing them to create much crisper and discrete outputs. GANs can be used to perform image processing, video generation and prediction, among other computer vision applications. GANs can also be utilised for a variety of science-related activities, including protein engineering, astronomical data processing, remote sensing image dehazing, and crystal structure synthesis. Other notable fields where GANs have made gains include finance, marketing, fashion design, sports, and music. Therefore in this article we provide a comprehensive overview of the applications of GANs in a wide variety of disciplines. We first cover the theory supporting GAN, GAN variants, and the metrics to evaluate GANs. Then we present how GAN and its variants can be applied in twelve domains, ranging from STEM fields, such as astronomy and biology, to business fields, such as marketing and finance, and to arts, such as music. As a result, researchers from other fields may grasp how GANs work and apply them to their own study. To the best of our knowledge, this article provides the most comprehensive survey of GAN's applications in different field INDEX TERMS deep learning, generative adversarial networks, computer vision, time series, applications

Review and Experimental Comparison of Generative Adversarial Networks for Synthetic Image Generation

“…The architecture of the Deep Convolutional Generative Adversarial Network (DCGAN) replaces the multilayered perception network with the deep convolutional artificial neural network, ensuring stable training of the generative component (Dash et al, 2023). The methodology is designed to project the input of the generator as a high-dimensional tensor and uses convolutional operations to generate the output image.…”

“…Both the input and output images are fed into a discriminator that evaluates whether the resulting image is suitably transformed from the original input. Adversarial loss guides the training of the generator, ensuring credible output, and an L1 loss coefficient updates the generator based on the disparity between the synthetic and desired output images (Dash et al, 2023).…”

NC2C-TransCycleGAN: Non-Contrast to Contrast-Enhanced CT Image Synthesis Using Transformer CycleGAN

“…With the wide application of Generative Adversarial Networks (GAN) in image generation (Skandarani et al, 2023), these problems are expected to be solved. In recent years GAN has been widely used in medical image tasks such as image segmentation (Beji et al, 2023;Dash et al, 2023;Skandarani et al, 2023;Zhong et al, 2023), lesion classification (Chen et al, 2023;Fan et al, 2023), and lesion detection (Esmaeili et al, 2023;Vyas & Rajendran, 2023). And the study of GAN in medical image synthesis tasks has dominated.…”

Enhancing electrical resistance tomography reconstruction from conductive fabric: a comparative study of CycleGAN and pix2pixGAN

“…Trained together through adversarial processes, they enhance each other's performance, yielding highly realistic data. GANs find diverse applications in fields like computer vision, natural language processing, and medical imaging, improving tasks such as image super-resolution and anomaly detection [27][28][29].…”