Refine
Year of publication
Document Type
- Article (unreviewed) (566) (remove)
Is part of the Bibliography
- yes (566)
Keywords
- Schule (11)
- Bildung (8)
- Arbeitszeugnis (7)
- Export (7)
- Digitalisierung (6)
- Energieversorgung (6)
- Nachhaltigkeit (6)
- Recht (6)
- Datenschutz (5)
- Dünnschichtchromatographie (5)
Institute
- Fakultät Medien und Informationswesen (M+I) (bis 21.04.2021) (189)
- Fakultät Wirtschaft (W) (120)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (97)
- Fakultät Elektrotechnik und Informationstechnik (E+I) (bis 03/2019) (95)
- Fakultät Medien (M) (ab 22.04.2021) (35)
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (27)
- INES - Institut für nachhaltige Energiesysteme (21)
- IMLA - Institute for Machine Learning and Analytics (16)
- IfTI - Institute for Trade and Innovation (13)
- IUAS - Institute for Unmanned Aerial Systems (4)
Open Access
- Closed Access (156)
- Open Access (131)
- Closed (71)
- Diamond (17)
- Bronze (15)
- Gold (1)
- Grün (1)
- Hybrid (1)
Sharing Economy
(2019)
Unternehmerische Resilienz
(2019)
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 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.