Exploiting Learned Symmetries in Group Equivariant Convolutions

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

2 Citations (Scopus)


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. All code is publicly available at github.com/Attila94/SepGrouPy.
Original languageEnglish
Title of host publication2021 IEEE International Conference on Image Processing (ICIP)
Subtitle of host publicationProceedings
Place of PublicationPiscataway
Number of pages5
ISBN (Electronic)978-1-6654-4115-5
ISBN (Print)978-1-6654-3102-6
Publication statusPublished - 2021
Event2021 IEEE International Conference on Image Processing (ICIP) - Virtual at Anchorage, United States
Duration: 19 Sept 202122 Sept 2021


Conference2021 IEEE International Conference on Image Processing (ICIP)
Country/TerritoryUnited States
CityVirtual at Anchorage


  • group equivariant convolutions
  • depth-wise separable convolutions
  • efficient deep learning


Dive into the research topics of 'Exploiting Learned Symmetries in Group Equivariant Convolutions'. Together they form a unique fingerprint.

Cite this