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

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 (e.g. 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 splitIn 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 (e.g. 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.…zeige mehrzeige weniger

Metadaten exportieren

Weitere Dienste

Suche bei Google Scholar

Statistik

frontdoor_oas
Metadaten
Dokumentart:Preprint
Zitierlink: https://opus.hs-offenburg.de/3958
Bibliografische Angaben
Titel (Englisch):Stabilizing GANs with Octave Convolutions
Verfasserangaben:Ricard Durall Lopez, Franz-Josef Pfreundt, Janis KeuperStaff MemberORCiDGND
Erscheinungsjahr:2019
Verlag:arXiv e-print
Seitenanzahl:8
Sprache:Englisch
Inhaltliche Informationen
Fakultäten / Einrichtungen:Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019)
Sammlungen der Hochschule Offenburg:Bibliografie
DDC-Sachgruppen:000 Allgemeines, Informatik, Informationswissenschaft
Freies Schlagwort / Tag:Machine Learning
Formale Angaben
Open-Access-Status: Open Access 
Lizenz (Deutsch):License LogoUrheberrechtlich geschützt
Kommentar:
last revised 17 Dec 2020
ArXiv-Id:http://arxiv.org/abs/1905.12534