Few Data Diversification in Training Generative Adversarial Networks | Zendy

Lucas Fontes Buzutti | Zendy; Carlos Eduardo Thomaz | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Few Data Diversification in Training Generative Adversarial Networks

Author(s) -

Lucas Fontes Buzutti,

Carlos Eduardo Thomaz

Publication year - 2021

Language(s) - English

Resource type - Conference proceedings

DOI - 10.5753/wvc.2021.18892

Subject(s) - generative grammar , diversification (marketing strategy) , computer science , adversarial system , training set , training (meteorology) , image (mathematics) , artificial intelligence , sample (material) , variation (astronomy) , data modeling , pattern recognition (psychology) , computer vision , machine learning , geography , chemistry , physics , chromatography , marketing , database , meteorology , astrophysics , business

The first GANs have initially produced sharp images in relatively small resolution and with limited variations, and unstable training. Later works proposed new GAN models capable of generating sharp images in high resolution and with a high level of variation. However, these models use unlimited and highly diversified image sets. We discuss here the use of these models with real-world image sets, since they are composed of limited sample size sets.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research