Collaborative-GAN: An Approach for Stabilizing the Training Process of Generative Adversarial Network

Generative Adversarial Network (GAN) outperforms its peers in the generative models’ family and is widely used to generate realistic samples in various domains. The basic idea of GAN is a competition between two networks called a generator and discriminator. Throughout the training process of...

Full description

Bibliographic Details

Main Authors:	Mohammed Megahed, Ammar Mohammed
Format:	Artigo
Language:	Inglês
Published:	IEEE 2024-01-01
Series:	IEEE Access
Subjects:	Generative adversarial network transfer learning training instability mode collapse
Online Access:	https://ieeexplore.ieee.org/document/10677438/
Tags:	Add Tag No Tags, Be the first to tag this record!