REViT: Roto-reflection Equivariant Convolutional Vision Transformer
Not on the map. Why?
Abstract (arXiv)
In this paper, we propose a discrete roto-reflection group equivariant vision transformer with convolutional attention. Roto-reflection equivariant networks preserve the rotational, flip and positional symmetry in feature maps, making them useful for tasks where orientation of the inputs is relevant to the model outputs. In image classification and object detection, most of the studies on roto-reflection equivariant models have focused on using convolutional neural networks rather than vision transformers. In this paper, we examine the challenges involved in achieving equivariance in vision transformers, and we propose a simpler way to implement a discretized roto-reflection group equivariant vision transformer. The experimental results demonstrate that our approach outperforms the existing approaches for developing discrete roto-reflection group equivariant neural networks for image classification.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 40 of its 52 references that are in the map. First posted on arXiv 24 Jun 2026.
Builds on
40 of 52 references.
References · 40
- 2017Attention Is All You Needcited by 60,361
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2016Group Equivariant Convolutional Networkscited by 1,165
- 2018Self-Attention with Relative Position Representationscited by 1,120
- 2021Transformers in Vision: A Surveycited by 1,013
- 2021E(n) Equivariant Graph Neural Networkscited by 965
- 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
- 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
- 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
- 2020A Survey on Visual Transformercited by 654
- 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
- 2018Spherical CNNscited by 456
28 more
- 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
- 2018Rotation Equivariant CNNs for Digital Pathologycited by 422
- 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 305
- 2018On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groupscited by 300
- 2016Harmonic Networks: Deep Translation and Rotation Equivariancecited by 295
- 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 264
- 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 248
- 2020Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Datacited by 248
- 2018A General Theory of Equivariant CNNs on Homogeneous Spacescited by 228
- 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 207
- 2023EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representationscited by 204
- 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 203
- 2016Rotation equivariant vector field networkscited by 99
- 2018Roto-Translation Covariant Convolutional Networks for Medical Image Analysiscited by 92
- 2021Equivariant Point Network for 3D Point Cloud Analysiscited by 81
- 2020On the Universality of Rotation Equivariant Point Cloud Networkscited by 80
- 2020Attentive Group Equivariant Convolutional Networkscited by 63
- 2020Group Equivariant Stand-Alone Self-Attention For Visioncited by 63
- 2020A Wigner-Eckart Theorem for Group Equivariant Convolution Kernelscited by 46
- 2020CNNs on Surfaces using Rotation-Equivariant Featurescited by 43
- 2022The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetrycited by 33
- 2022VN-Transformer: Rotation-Equivariant Attention for Vector Neuronscited by 27
- 2022Self-Supervised Equivariant Learning for Oriented Keypoint Detectioncited by 26
- 2016Learning rotation invariant convolutional filters for texture classificationcited by 24
- 2022What is an equivariant neural network?cited by 21
- 2016Permutation-equivariant neural networks applied to dynamics predictioncited by 14
- 2023E(2)-Equivariant Graph Planning for Navigationcited by 6
- 20243D Equivariant Pose Regression via Direct Wigner-D Harmonics Predictioncited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.