Latent Space Conditioning on Generative Adversarial Networks
- 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 Although early successes were mostly unsupervised, bit by bit, this trend has been superseded by approaches based on labelled data.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 ofGenerative 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 Although early successes were mostly unsupervised, bit by bit, this trend has been superseded by approaches based on labelled data.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.…
Document Type: | Conference Proceeding |
---|---|
Conference Type: | Konferenzartikel |
Zitierlink: | https://opus.hs-offenburg.de/5290 | Bibliografische Angaben |
Title (English): | Latent Space Conditioning on Generative Adversarial Networks |
Conference: | VISIGRAPP 2021: International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (16. : February 8-10, 2021 : Vienna, Austria) |
Author: | Ricard Durall Lopez, Kalun Ho, Franz-Josef Pfreundt, Janis KeuperStaff MemberORCiDGND |
Year of Publication: | 2021 |
Publisher: | SciTePress |
First Page: | 24 |
Last Page: | 34 |
Parent Title (English): | Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications |
Editor: | Giovanni Maria Farinella, Petia Radeva, Jose Braz, Kadi Bouatouch |
Volume: | 4 |
ISBN: | 978-989-758-488-6 |
ISSN: | 2184-4321 |
DOI: | https://doi.org/10.5220/0010178800240034 |
URL: | https://www.scitepress.org/Papers/2021/101788/101788.pdf |
Language: | English | Inhaltliche Informationen |
Institutes: | Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) |
Forschung / IMLA - Institute for Machine Learning and Analytics | |
Institutes: | Bibliografie |
Tag: | Generative Adversarial Network; Representation Learning; Unsupervised Conditional Training | Formale Angaben |
Open Access: | Open Access |
Licence (German): | Creative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International |