Volltext-Downloads (blau) und Frontdoor-Views (grau)
  • search hit 523 of 1253
Back to Result List

Stabilizing GANs with Octave Convolutions

  • In this preliminary report, we present a simple but very effective technique to stabilize the training of CNN based GANs. Motivated by recently published methods using frequency decomposition of convolutions (eg Octave Convolutions), we propose a novel convolution scheme to stabilize the training and reduce the likelihood of a mode collapse. The basic idea of our approach is to split convolutionalIn this preliminary report, we present a simple but very effective technique to stabilize the training of CNN based GANs. Motivated by recently published methods using frequency decomposition of convolutions (eg Octave Convolutions), we propose a novel convolution scheme to stabilize the training and reduce the likelihood of a mode collapse. The basic idea of our approach is to split convolutional filters into additive high and low frequency parts, while shifting weight updates from low to high during the training. Intuitively, this method forces GANs to learn low frequency coarse image structures before descending into fine (high frequency) details. Our approach is orthogonal and complementary to existing stabilization methods and can simply plugged into any CNN based GAN architecture. First experiments on the CelebA dataset show the effectiveness of the proposed method.show moreshow less

Export metadata

Additional Services

Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Document Type:Conference Proceeding
Conference Type:Konferenzartikel
Zitierlink: https://opus.hs-offenburg.de/5288
Bibliografische Angaben
Title (English):Stabilizing GANs with Octave Convolutions
Conference:VISIGRAPP: International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (16. : February 8-10, 2021)
Author:Ricard Durall Lopez, Franz-Josef Pfreundt, Janis KeuperStaff MemberORCiDGND
Year of Publication:2021
Publisher:SciTePress
First Page:15
Last Page:23
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/10.5220/0010178700150023
URL:https://www.scitepress.org/Papers/2021/101787/101787.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
DDC classes:000 Allgemeines, Informatik, Informationswissenschaft
Tag:Generative Adversarial Network; Octave Convolution; Regularization; Stability
Formale Angaben
Open Access: Open Access 
Licence (German):License LogoCreative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International