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

M Megahed, A Mohammed - Wiley Interdisciplinary Reviews …, 2024 - Wiley Online Library
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 …

On data augmentation for GAN training

NT Tran, VH Tran, NB Nguyen… - … on Image Processing, 2021 - ieeexplore.ieee.org
Recent successes in Generative Adversarial Networks (GAN) have affirmed the importance
of using more data in GAN training. Yet it is expensive to collect data in many domains such …

Global evolution of research in artificial intelligence in health and medicine: a bibliometric study

BX Tran, GT Vu, GH Ha, QH Vuong, MT Ho… - Journal of clinical …, 2019 - mdpi.com
The increasing application of Artificial Intelligence (AI) in health and medicine has attracted
a great deal of research interest in recent decades. This study aims to provide a global and …

Deep clustering by gaussian mixture variational autoencoders with graph embedding

L Yang, NM Cheung, J Li… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
We propose DGG: D eep clustering via a G aussian-mixture variational autoencoder (VAE)
with G raph embedding. To facilitate clustering, we apply Gaussian mixture model (GMM) as …

Infomax-gan: Improved adversarial image generation via information maximization and contrastive learning

KS Lee, NT Tran, NM Cheung - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Abstract While Generative Adversarial Networks (GANs) are fundamental to many
generative modelling applications, they suffer from numerous issues. In this work, we …

LEGAN: Addressing intra-class imbalance in GAN-based medical image augmentation for improved imbalanced data classification

H Ding, N Huang, Y Wu, X Cui - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Currently, the medical image classification is challenged by performance degradation due to
imbalanced data. Balancing the data through sample augmentation proves to be an effective …

Self-supervised gan: Analysis and improvement with multi-class minimax game

NT Tran, VH Tran, BN Nguyen… - Advances in neural …, 2019 - proceedings.neurips.cc
Self-supervised (SS) learning is a powerful approach for representation learning using
unlabeled data. Recently, it has been applied to Generative Adversarial Networks (GAN) …

[PDF][PDF] Towards good practices for data augmentation in gan training

NT Tran, VH Tran, NB Nguyen, TK Nguyen… - arxiv preprint arxiv …, 2020 - researchgate.net
Recent successes in Generative Adversarial Networks (GAN) have affirmed the importance
of using more data in GAN training. Yet it is expensive to collect data in many domains such …

[HTML][HTML] Cyclic consistent image style transformation: from model to system

J Peng, K Chen, Y Gong, T Zhang, B Su - Applied Sciences, 2024 - mdpi.com
Generative Adversarial Networks (GANs) have achieved remarkable success in various
tasks, including image generation, editing, and reconstruction, as well as in unsupervised …

DFSGAN: Introducing editable and representative attributes for few-shot image generation

M Yang, S Niu, Z Wang, D Li, W Du - Engineering Applications of Artificial …, 2023 - Elsevier
Training generative adversarial networks (GANs) usually requires large-scale data and
massive computation resources. The performance of GANs plummets when given limited …