Volltext-Downloads (blau) und Frontdoor-Views (grau)

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 Although early successes were mostly unsupervised, bit by bit, this trend has been superseded by approaches based on labelled data.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 Although early successes were mostly unsupervised, bit by bit, this trend has been superseded by approaches based on labelled data.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.…zeige mehrzeige weniger

Metadaten exportieren

Weitere Dienste

Suche bei Google Scholar

Statistik

frontdoor_oas
Metadaten
Dokumentart:Konferenzveröffentlichung
Art der Konferenzveröffentlichung:Konferenzartikel
Zitierlink: https://opus.hs-offenburg.de/5290
Bibliografische Angaben
Titel (Englisch):Latent Space Conditioning on Generative Adversarial Networks
Konferenzangaben:VISIGRAPP 2021: International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (16. : February 8-10, 2021 : Vienna, Austria)
Verfasserangaben:Ricard Durall Lopez, Kalun Ho, Franz-Josef Pfreundt, Janis KeuperStaff MemberORCiDGND
Erscheinungsjahr:2021
Verlag:SciTePress
Erste Seite:24
Letzte Seite:34
Titel des übergeordneten Werkes (Englisch):Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Herausgeber*in:Giovanni Maria Farinella, Petia Radeva, Jose Braz, Kadi Bouatouch
Jahrgang (Band):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
Sprache:Englisch
Inhaltliche Informationen
Fakultäten / Einrichtungen:Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019)
Forschung:IMLA - Institute for Machine Learning and Analytics
Sammlungen der Hochschule Offenburg:Bibliografie
Freies Schlagwort / Tag:Generative Adversarial Network; Representation Learning; Unsupervised Conditional Training
Formale Angaben
Open-Access-Status: Open Access 
Lizenz (Deutsch):License LogoCreative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International