Code underlying the publication: Exploiting Learned Symmetries in Group Equivariant Convolutions

doi: 10.4121/5be76022-2db7-4d5d-acb8-6d42fa86f0df.v1
The doi above is for this specific version of this dataset, which is currently the latest. Newer versions may be published in the future. For a link that will always point to the latest version, please use
doi: 10.4121/5be76022-2db7-4d5d-acb8-6d42fa86f0df
Datacite citation style:
Attila Lengyel; van Gemert, Jan (2023): Code underlying the publication: Exploiting Learned Symmetries in Group Equivariant Convolutions. Version 1. 4TU.ResearchData. software.
Other citation styles (APA, Harvard, MLA, Vancouver, Chicago, IEEE) available at Datacite

Code corresponding to ICIP 2021 submission "Exploiting Learned Symmetries in Group Equivariant Convolutions".


Group Equivariant Convolutions (GConvs) enable convolutional neural networks to be equivariant to various transformation groups, but at an additional parameter and compute cost. We investigate the filter parameters learned by GConvs and find certain conditions under which they become highly redundant. We show that GConvs can be efficiently decomposed into depthwise separable convolutions while preserving equivariance properties and demonstrate improved performance and data efficiency on two datasets.

  • 2023-11-29 first online, published, posted
  • Tabula Inscripta: Prior knowledge for deep learning (grant code VI.Vidi.192.100) [more info...] Dutch Research Council
TU Delft, TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, Department of Intelligent Systems, Computer Vision Lab


To access the source code, use the following command:

git clone