mlsanityData to 7 Oct 2026

Equivariant Transformer Networks

arXiv 1901.11399 ↗First posted 25 Jan 2019cs.CV cs.LG stat.MLcited by 35

Not on the map. Why?

Abstract (arXiv)

How can prior knowledge on the transformation invariances of a domain be incorporated into the architecture of a neural network? We propose Equivariant Transformers (ETs), a family of differentiable image-to-image mappings that improve the robustness of models towards pre-defined continuous transformation groups. Through the use of specially-derived canonical coordinate systems, ETs incorporate functions that are equivariant by construction with respect to these transformations. We show empirically that ETs can be flexibly composed to improve model robustness towards more complicated transformation groups in several parameters. On a real-world image classification task, ETs improve the sample efficiency of ResNet classifiers, achieving relative improvements in error rate of up to 15% in the limited data regime while increasing model parameter count by less than 1%.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 7; 2023: 7; 2024: 3; 2025: 8; 2026: 1.

35 papers.

Sort:

  1. 2021Choose a Transformer: Fourier or Galerkincited by 333
  2. 2022Equivariance with Learned Canonicalization Functionscited by 106
  3. 2021Deep Learning for UAV-based Object Detection and Tracking: A Surveycited by 33
  4. 2023PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learningcited by 31
  5. 2021RoI Tanh-polar Transformer Network for Face Parsing in the Wildcited by 23
  6. 2021Self-Interpretable Model with TransformationEquivariant Interpretationcited by 21
  7. 2022Maximum Class Separation as Inductive Bias in One Matrixcited by 21
  8. 2025Learning the RoPEs: Better 2D and 3D Position Encodings with STRINGcited by 19
  9. 2022Equivariance Discovery by Learned Parameter-Sharingcited by 18
  10. 2024LieRE: Lie Rotational Positional Encodingscited by 16
  11. 2021Addressing the Topological Defects of Disentanglement via Distributed Operatorscited by 14
  12. 2023Spatially Covariant Lesion Segmentationcited by 10
23 more
  1. 2021Training or Architecture? How to Incorporate Invariance in Neural Networkscited by 9
  2. 2022Improving the Sample-Complexity of Deep Classification Networks with Invariant Integrationcited by 7
  3. 2024Tilt your Head: Activating the Hidden Spatial-Invariance of Classifierscited by 7
  4. 2024Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networkscited by 6
  5. 2022Robust Self-Supervised Learning with Lie Groupscited by 4
  6. 2023Using and Abusing Equivariancecited by 4
  7. 2023Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictorscited by 3
  8. 2025Group Downsampling with Equivariant Anti-aliasingcited by 3
  9. 2025Geometrically Constrained and Token-Based Probabilistic Spatial Transformerscited by 3
  10. 2025Emergent Riemannian geometry over learning discrete computations on continuous manifoldscited by 3
  11. 2022A Simple Strategy to Provable Invariance via Orbit Mappingcited by 2
  12. 2023Efficient Rotation Invariance in Deep Neural Networks through Artificial Mental Rotationcited by 2
  13. 2025Artificial Intelligence for Direct Prediction of Molecular Dynamics Across Chemical Spacecited by 2
  14. 2021FILTRA: Rethinking Steerable CNN by Filter Transformcited by 1
  15. 2021Invariance-based Multi-Clustering of Latent Space Embeddings for Equivariant Learningcited by 1
  16. 2021Augmenting Imitation Experience via Equivariant Representationscited by 1
  17. 2022Perspective Transformation Layercited by 1
  18. 2025Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problemscited by 1
  19. 2025RNNs perform task computations by dynamically warping neural representationscited by 1
  20. 2023Subspace-Configurable Networkscited by 0
  21. 2023Occlusion-Aware Deep Convolutional Neural Network via Homogeneous Tanh-transforms for Face Parsingcited by 0
  22. 2025LaPON: A Lagrange's-mean-value-theorem-inspired operator network for solving PDEs and its application on NSEcited by 0
  23. 2026A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of O(2)cited by 0