Volltext-Downloads (blau) und Frontdoor-Views (grau)
  • search hit 23 of 175
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 (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.show moreshow less

Export metadata

Additional Services

Share in Twitter Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author:Ricard Durall Lopez, Franz-Josef Pfreundt, Janis KeuperORCiDGND
Publisher:arXiv e-print
Year of Publication:2019
Page Number:8
Language:English
Tag:Machine Learning
DDC classes:000 Allgemeines, Informatik, Informationswissenschaft
Document Type:Article (unreviewed)
Open Access:Frei zugänglich
Institutes:Bibliografie
Release Date:2020/01/21
Licence (German):License LogoEs gilt das UrhG
Note:
last revised 17 Dec 2020
ArXiv Id:http://arxiv.org/abs/1905.12534