Authors:
Ricard Durall
1
;
2
;
3
;
Kalun Ho
4
;
1
;
2
;
Franz-Josef Pfreundt
2
and
Janis Keuper
2
;
5
Affiliations:
1
Fraunhofer Center Machine Learning, Germany
;
2
Fraunhofer ITWM, Germany
;
3
IWR, University of Heidelberg, Germany
;
4
Data and Web Science Group, University of Mannheim, Germany
;
5
Institute for Machine Learning and Analytics, Offenburg University, Germany
Keyword(s):
Generative Adversarial Network, Unsupervised Conditional Training, Representation Learning.
Abstract:
Generative adversarial networks are the state of the art approach towards learned synthetic image generation. Although early successes were mostly unsupervised, bit by bit, this trend has been superseded by approaches based on labelled data. These supervised methods allow a much finer-grained control of the output image, offering more flexibility and stability. Nevertheless, the main drawback of such models is the necessity of annotated data. In this work, we introduce an novel framework that benefits from two popular learning techniques, adversarial training and representation learning, and takes a step towards unsupervised conditional GANs. In particular, our approach exploits the structure of a latent space (learned by the representation learning) and employs it to condition the generative model. In this way, we break the traditional dependency between condition and label, substituting the latter by unsupervised features coming from the latent space. Finally, we show that this new
technique is able to produce samples on demand keeping the quality of its supervised counterpart.
(More)