Towards Deeper Generative Architectures for GANs using Dense connections

In this paper, we present the result of adopting skip connections and dense layers, previously used in image classification tasks, in the Fisher GAN implementation. We have experimented with different numbers of layers and inserting these connections in different sections of the network. Our finding...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2018-11
Hauptverfasser:	Tripathi, Samarth, Tu, Renbo
Format:	Artikel
Sprache:	eng
Schlagworte:	Image classification
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!