Investigating Object Compositionality in Generative Adversarial Networks

Deep generative models seek to recover the process with which the observed data was generated. They may be used to synthesize new samples or to subsequently extract representations. Successful approaches in the domain of images are driven by several core inductive biases. However, a bias to account...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-07
Hauptverfasser:	Sjoerd van Steenkiste, Kurach, Karol, Schmidhuber, Jürgen, Gelly, Sylvain
Format:	Artikel
Sprache:	eng
Schlagworte:	Bias Computer Science - Computer Vision and Pattern Recognition Computer Science - Neural and Evolutionary Computing Generative adversarial networks Representations
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!