mlsanityData to 14 Oct 2026

Exploiting Learned Symmetries in Group Equivariant Convolutions

arXiv 2106.04914 ↗First posted 9 Jun 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 17 of its 21 references that are in the map. First posted on arXiv 9 Jun 2021.

Builds on

17 of 21 references.

References · 17

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  2. 2019Searching for MobileNetV3cited by 1,994
  3. 2016Group Equivariant Convolutional Networkscited by 1,165
  4. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 354
  5. 2016Harmonic Networks: Deep Translation and Rotation Equivariancecited by 295
  6. 2017Learning Steerable Filters for Rotation Equivariant CNNscited by 194
  7. 2020On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Locationcited by 142
  8. 2019Deep Scale-spaces: Equivariance Over Scalecited by 114
  9. 2019Scale-Equivariant Steerable Networkscited by 110
  10. 2018Roto-Translation Covariant Convolutional Networks for Medical Image Analysiscited by 92
  11. 2020Attentive Group Equivariant Convolutional Networkscited by 63
  12. 2018CubeNet: Equivariance to 3D Rotation and Translationcited by 59
5 more
  1. 2020Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNetscited by 28
  2. 2017Deep Rotation Equivariant Networkcited by 16
  3. 2020Boosting Deep Neural Networks with Geometrical Prior Knowledge: A Surveycited by 12
  4. 2019Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring In Datacited by 10
  5. 2020A Data and Compute Efficient Design for Limited-Resources Deep Learningcited by 10

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 0; 2023: 2; 2024: 0; 2025: 1.

5 papers.

  1. 2021Learning Partial Equivariances from Datacited by 45
  2. 2021Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groupscited by 22
  3. 2023What Affects Learned Equivariance in Deep Image Recognition Models?cited by 15
  4. 2025Flopping for FLOPs: Leveraging equivariance for computational efficiencycited by 8
  5. 2023Color Equivariant Convolutional Networkscited by 7