Utilizing Amari-Alpha Divergence to Stabilize the Training of Generative Adversarial Networks

Generative Adversarial Nets (GANs) are one of the most popular architectures for image generation, which has achieved significant progress in generating high-resolution, diverse image samples. The normal GANs are supposed to minimize the Kullback–Leibler divergence between distributions of natural a...

Descripción completa

Detalles Bibliográficos
Autores principales: Cai, Likun, Chen, Yanjie, Cai, Ning, Cheng, Wei, Wang, Hao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7516886/
https://www.ncbi.nlm.nih.gov/pubmed/33286184
http://dx.doi.org/10.3390/e22040410

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7516886/
https://www.ncbi.nlm.nih.gov/pubmed/33286184
http://dx.doi.org/10.3390/e22040410

Ejemplares similares