On conditioning GANs to hierarchical ontologies

Autoren Hamid Eghbal-zadeh
Lukas Fischer
Thomas Hoch
Editoren G. Anderst-Kotsis
A Min Tjoa
I. Khalil
et al.
Titel On conditioning GANs to hierarchical ontologies
Buchtitel Database and Expert Systems Applications - Proc DEXA 209 International Workshops
Typ in Konferenzband
Verlag Springer
Serie Communications in Computer and Information Science
Band 1062
ISBN 978-3-030-27683-6
DOI 10.1007/978-3-030-27684-3_23
Monat August
Jahr 2019
Seiten 182-186
SCCH ID# 19038

The recent success of Generative Adversarial Networks (GAN) is a result of their ability to generate high quality images given samples from a latent space. One of the applications of GANs is to generate images from a text description, where the text is first encoded and further used for the conditioning in the generative model. In addition to text, conditional generative models often use label information for conditioning. Hence, the structure of the meta-data and the ontology of the labels is important for such models. In this paper, we propose Ontology Generative Adversarial Networks (O-GANs) to handle the complexities of the data with label ontology. We evaluate our model on a dataset of fashion images with hierarchical label structure. Our results suggest that the incorporation of the ontology, leads to better image quality as measured by Fréchet Inception Distance and Inception Score. Additionally, we show that the O-GAN better matches the generated images to their conditioning text, compared to models that do not incorporate the label ontology.