Volltext-Downloads (blau) und Frontdoor-Views (grau)
The search result changed since you submitted your search request. Documents might be displayed in a different sort order.
  • search hit 41 of 566
Back to Result List

Semi Few-Shot Attribute Translation

  • Recent studies have shown remarkable success in image-to-image translation for attribute transfer applications. However, most of existing approaches are based on deep learning and require an abundant amount of labeled data to produce good results, therefore limiting their applicability. In the same vein, recent advances in meta-learning have led to successful implementations with limited availableRecent studies have shown remarkable success in image-to-image translation for attribute transfer applications. However, most of existing approaches are based on deep learning and require an abundant amount of labeled data to produce good results, therefore limiting their applicability. In the same vein, recent advances in meta-learning have led to successful implementations with limited available data, allowing so-called few-shot learning. In this paper, we address this limitation of supervised methods, by proposing a novel approach based on GANs. These are trained in a meta-training manner, which allows them to perform image-to-image translations using just a few labeled samples from a new target class. This work empirically demonstrates the potential of training a GAN for few shot image-to-image translation on hair color attribute synthesis tasks, opening the door to further research on generative transfer learning.show moreshow less

Export metadata

Additional Services

Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Document Type:Article (unreviewed)
Zitierlink: https://opus.hs-offenburg.de/3957
Bibliografische Angaben
Title (English):Semi Few-Shot Attribute Translation
Author:Ricard Durall Lopez, Franz-Josef Pfreundt, Janis KeuperStaff MemberORCiDGND
Year of Publication:2019
Publisher:arXiv e-print
Page Number:9
Language:English
Inhaltliche Informationen
Institutes:Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019)
Institutes:Bibliografie
DDC classes:000 Allgemeines, Informatik, Informationswissenschaft
Formale Angaben
Open Access: Open Access 
Licence (German):License LogoUrheberrechtlich geschützt
ArXiv Id:http://arxiv.org/abs/1910.03240