cff-version: 1.2.0
abstract: "<p>Code corresponding to ICIP 2021 submission "Exploiting Learned Symmetries in Group Equivariant Convolutions".</p><p><br></p><p><strong>Abstract</strong></p><p>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.</p>"
authors:
  - family-names: Lengyel
    given-names: Attila
    orcid: "https://orcid.org/0000-0002-2982-2003"
  - family-names: van Gemert
    given-names: Jan
    orcid: "https://orcid.org/0000-0002-6913-0482"
title: "Code underlying the publication: Exploiting Learned Symmetries in Group Equivariant Convolutions"
keywords:
version: 1
identifiers:
  - type: doi
    value: 10.4121/5be76022-2db7-4d5d-acb8-6d42fa86f0df.v1
license: MIT
date-released: 2023-11-29