Enhanced balancing GAN: minority-class image generation

Generative adversarial networks (GANs) are one of the most powerful generative models, but always require a large and balanced dataset to train. Traditional GANs are not applicable to generate minority-class images in a highly imbalanced dataset. Balancing GAN (BAGAN) is proposed to mitigate this pr...

Descripción completa

Detalles Bibliográficos
Autores principales: Huang, Gaofeng, Jafari, Amir Hossein
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer London 2021
Materias:
Original Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8211314/
https://www.ncbi.nlm.nih.gov/pubmed/34177125
http://dx.doi.org/10.1007/s00521-021-06163-8

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8211314/
https://www.ncbi.nlm.nih.gov/pubmed/34177125
http://dx.doi.org/10.1007/s00521-021-06163-8

Ejemplares similares