DGattGAN: Cooperative Up-Sampling Based Dual Generator Attentional GAN on Text-to-Image Synthesis

Zhang, Han; Zhu, Hongqing; Yang, Suyi; Li, Wenhao

doi:10.1109/access.2021.3058674

Cited by 14 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, MRP-GAN (Qi, Fan, et al, 2021), SAM-GAN (Peng et al, 2021), DM-GAN (M. Zhu, Pan, et al, 2019), DAE-GAN (Ruan et al, 2021), KT-GAN (Tan et al, 2021), Bridge-GAN (M. Yuan & Peng, 2020), CF-GAN (Y. Zhang, Han, et al, 2022), DGattGAN (H. Zhang, Zhu, et al, 2021), PCCM-GAN (Qi, Sun, et al, 2021), aRTIC GAN (Alati et al, 2022), and CDRGAN (M. Wang et al, 2021) were proposed to generate natural images based on a descriptive texts that describe these images. Likewise, Y. Zhou (2021), M. Z.…”

Section: Text-to-image Translationmentioning

confidence: 99%

“…This GAN model takes both image and a text that describes an object to generate a new image containing this object. Also, MRP‐GAN (Qi, Fan, et al, 2021), SAM‐GAN (Peng et al, 2021), DM‐GAN (M. Zhu, Pan, et al, 2019), DAE‐GAN (Ruan et al, 2021), KT‐GAN (Tan et al, 2021), Bridge‐GAN (M. Yuan & Peng, 2020), CF‐GAN (Y. Zhang, Han, et al, 2022), DGattGAN (H. Zhang, Zhu, et al, 2021), PCCM‐GAN (Qi, Sun, et al, 2021), aRTIC GAN (Alati et al, 2022), and CDRGAN (M. Wang et al, 2021) were proposed to generate natural images based on a descriptive texts that describe these images. Likewise, Y. Zhou (2021), M. Z. Khan et al (2021), and Y. Zhou and Shimada (2021) proposed GAN models to synthesize face images based on the text describing these faces.…”

Section: Gan Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

A comprehensive review of generative adversarial networks: Fundamentals, applications, and challenges

Mohammed

2023

WIREs Computational Stats

View full text Add to dashboard Cite

In machine learning, a generative model is responsible for generating new samples of data in terms of a probabilistic model. Generative adversarial network (GAN) has been widely used to generate realistic samples in different domains and outperforms its peers in the generative models family. However, producing a robust GAN model is not a trivial task because many challenges face the GAN during the training process and impact its performance, affecting the quality and diversity of the generated samples. In this article, we conduct a comprehensive review of GANs to present the fundamentals of GAN, including its components, types, and objective functions. Also, we present an overview of the evaluation matrices used to evaluate GAN models. Moreover, we list the applications of GANs and research work in various domains. Finally, we present the challenges that face GANs and highlight two significant issues, representing mode collapse and training instability, in addition to those research efforts that tackle these challenges.This article is categorized under: Statistical Learning and Exploratory Methods of the Data Sciences > Deep Learning Statistical Learning and Exploratory Methods of the Data Sciences > Neural Networks

show abstract

Section: Text-to-image Translationmentioning

confidence: 99%

Section: Gan Applicationsmentioning

confidence: 99%

A comprehensive review of generative adversarial networks: Fundamentals, applications, and challenges

Mohammed

2023

WIREs Computational Stats

View full text Add to dashboard Cite

show abstract

“…In this approach, the generator incorporates a dynamic selection mechanism to match text features with image features, enabling more accurate synthesis. Meanwhile, the discriminator utilizes a multi-class discriminant method, where mask segmentation is introduced as an additional type to enhance its discrimination capacity 23 . The proposed framework, called RaSeedGAN (RAndomly-SEEDed super-resolution GAN), is designed to evaluate field quantities from randomly sparse sensors without relying on full-field high-resolution training.…”

Section: Related Workmentioning

confidence: 99%

Deep neural architecture for natural language image synthesis for Tamil text using BASEGAN and hybrid super resolution GAN (HSRGAN)

Diviya,

Karmel

2023

Sci Rep

View full text Add to dashboard Cite

Tamil is a language that has the most extended history and is a conventional language of India. It has antique origins and a distinct tradition. A study reveals that at the beginning of the twenty-first century, more than 66 million people spoke Tamil. In the present time, image synthesis from text emerged as a promising advancement in computer vision applications. The research work done so far in intelligent systems is trained in universal language but still has not achieved the desired development level in regional languages. Regional languages have a greater scope for developing applications and will enhance more research areas to be explored, ruling out the barrier. The current work using Auto Encoders failed at the point of providing vivid information along with essential descriptions of the synthesised images. The work aims to generate embedding vectors using a language model headed by image synthesis using GAN (Generative Adversarial Network) architecture. The proposed method is divided into two stages: designing a language model TBERTBASECASE model for generating embedding vectors. Synthesising images using Generative Adversarial Network called BASEGAN, the resolution has been improved through two-stage architecture named HYBRID SUPER RESOLUTION GAN. The work uses Oxford-102 and CUB-200 datasets. The framework efficiency has been measured using F1 Score, Fréchet inception distance (FID), and Inception Score (IS). Language and image synthesis architecture proposed can bridge the gap between the research ideas in regional languages.

show abstract

Generative Adversarial Network for Synthetic Image Generation Method: Review, Analysis, and Perspective

Dewi

2024

Applications of Generative AI

View full text Add to dashboard Cite

DGattGAN: Cooperative Up-Sampling Based Dual Generator Attentional GAN on Text-to-Image Synthesis

Cited by 14 publications

References 21 publications

A comprehensive review of generative adversarial networks: Fundamentals, applications, and challenges

A comprehensive review of generative adversarial networks: Fundamentals, applications, and challenges

Deep neural architecture for natural language image synthesis for Tamil text using BASEGAN and hybrid super resolution GAN (HSRGAN)

Generative Adversarial Network for Synthetic Image Generation Method: Review, Analysis, and Perspective

Contact Info

Product

Resources

About