Investigating the effect of loss functions on single-image GAN performance

Loss functions are crucial in training generative adversarial networks (GANs) and shaping the resulting outputs. These functions, specifically designed for GANs, optimize generator and discriminator networks together but in opposite directions. GAN models, which typically handle large datasets, have...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of innovative science and engineering 2024-12, Vol.8 (2), p.213-225
Hauptverfasser:	Yıldız, Eyyüp, Yüksel, Erkan, Sevgen, Selçuk
Format:	Artikel
Sprache:	eng
Schlagworte:	generative adversarial networks image diversity loss functions low data regime single-image gan
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!