mlsanityData to 14 Oct 2026

Scale-Rotation-Equivariant Lie Group Convolution Neural Networks (Lie Group-CNNs)

arXiv 2306.06934 ↗First posted 12 Jun 2023cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

The weight-sharing mechanism of convolutional kernels ensures translation-equivariance of convolution neural networks (CNNs). Recently, rotation-equivariance has been investigated. However, research on scale-equivariance or simultaneous scale-rotation-equivariance is insufficient. This study proposes a Lie group-CNN, which can keep scale-rotation-equivariance for image classification tasks. The Lie group-CNN includes a lifting module, a series of group convolution modules, a global pooling layer, and a classification layer. The lifting module transfers the input image from Euclidean space to Lie group space, and the group convolution is parameterized through a fully connected network using Lie-algebra of Lie-group elements as inputs to achieve scale-rotation-equivariance. The Lie group SIM(2) is utilized to establish the Lie group-CNN with scale-rotation-equivariance. Scale-rotation-equivariance of Lie group-CNN is verified and achieves the best recognition accuracy on the blood cell dataset (97.50%) and the HAM10000 dataset (77.90%) superior to Lie algebra convolution network, dilation convolution, spatial transformer network, and scale-equivariant steerable network. In addition, the generalization ability of the Lie group-CNN on SIM(2) on rotation-equivariance is verified on rotated-MNIST and rotated-CIFAR10, and the robustness of the network is verified on SO(2) and SE(2). Therefore, the Lie group-CNN can successfully extract geometric features and performs equivariant recognition on images with rotation and scale transformations.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 12 Jun 2023.

Builds on

27 of 42 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  5. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  6. 2015Spatial Transformer Networkscited by 1,429
  7. 2016Group Equivariant Convolutional Networkscited by 1,165
  8. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
  9. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 720
  10. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 470
  11. 2019General E(2)-Equivariant Steerable CNNscited by 446
  12. 2018Rotation Equivariant CNNs for Digital Pathologycited by 422
15 more
  1. 2019Making Convolutional Networks Shift-Invariant Againcited by 391
  2. 2018On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groupscited by 300
  3. 2020Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Datacited by 248
  4. 2014Understanding image representations by measuring their equivariance and equivalencecited by 243
  5. 2018Why do deep convolutional networks generalize so poorly to small image transformations?cited by 198
  6. 2017Equivariance Through Parameter-Sharingcited by 141
  7. 2019Scale-Equivariant Steerable Networkscited by 110
  8. 2020Convolutional Networks with Dense Connectivitycited by 98
  9. 2019B-Spline CNNs on Lie Groupscited by 97
  10. 2015Rotation-invariant convolutional neural networks for galaxy morphology predictioncited by 83
  11. 2021Automatic Symmetry Discovery with Lie Algebra Convolutional Networkcited by 83
  12. 2014Scale-Invariant Convolutional Neural Networkscited by 40
  13. 2021Fourier Series Expansion Based Filter Parametrization for Equivariant Convolutionscited by 26
  14. 2019Learning Generalized Transformation Equivariant Representations via Autoencoding Transformationscited by 22
  15. 2021Equivariant Wavelets: Fast Rotation and Translation Invariant Wavelet Scattering Transformscited by 6

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024Relaxed Equivariance via Multitask Learningcited by 13
  2. 2025Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domainscited by 0