mlsanityData to 14 Oct 2026

Equivariant Representation Learning via Class-Pose Decomposition

arXiv 2207.03116 ↗First posted 7 Jul 2022cs.LG math.GRcited by 17

Not on the map. Why?

Abstract (arXiv)

We introduce a general method for learning representations that are equivariant to symmetries of data. Our central idea is to decompose the latent space into an invariant factor and the symmetry group itself. The components semantically correspond to intrinsic data classes and poses respectively. The learner is trained on a loss encouraging equivariance based on supervision from relative symmetry information. The approach is motivated by theoretical results from group theory and guarantees representations that are lossless, interpretable and disentangled. We provide an empirical investigation via experiments involving datasets with a variety of symmetries. Results show that our representations capture the geometry of data and outperform other equivariant representation learning frameworks.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 31 of its 41 references that are in the map. First posted on arXiv 7 Jul 2022.

Builds on

31 of 41 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2018World Modelscited by 1,513
  6. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
  7. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  8. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  9. 2016Group Equivariant Convolutional Networkscited by 1,165
  10. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  11. 2020A Survey on Contrastive Self-supervised Learningcited by 554
  12. 2018Gibson Env: Real-World Perception for Embodied Agentscited by 481
19 more
  1. 2018Spherical CNNscited by 456
  2. 2018Towards a Definition of Disentangled Representationscited by 296
  3. 2019Gauge Equivariant Convolutional Networks and the Icosahedral CNNcited by 267
  4. 2020Weakly-Supervised Disentanglement Without Compromisescited by 239
  5. 2018A General Theory of Equivariant CNNs on Homogeneous Spacescited by 228
  6. 2019Contrastive Learning of Structured World Modelscited by 209
  7. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
  8. 2020On Learning Sets of Symmetric Elementscited by 98
  9. 2018Explorations in Homeomorphic Variational Auto-Encodingcited by 65
  10. 2020Plannable Approximations to MDP Homomorphisms: Equivariance under Actionscited by 61
  11. 2022Learning Symmetric Embeddings for Equivariant World Modelscited by 54
  12. 2020Equivariant Neural Renderingcited by 48
  13. 2022Unsupervised Learning of Group Invariant and Equivariant Representationscited by 39
  14. 2017Interpretable Transformations with Encoder-Decoder Networkscited by 34
  15. 2022Symmetry-Based Representations for Artificial and Biological General Intelligencecited by 26
  16. 2021Towards Building A Group-based Unsupervised Representation Disentanglement Frameworkcited by 22
  17. 2020Learning Group Structure and Disentangled Representations of Dynamical Environmentscited by 13
  18. 2020Quantifying and Learning Linear Symmetry-Based Disentanglementcited by 9
  19. 2018Efficient conversion from rotating matrix to rotation axis and angle by extending Rodrigues' formulacited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 9; 2024: 1; 2025: 2; 2026: 3.

17 papers.

Sort:

  1. 2023A Cookbook of Self-Supervised Learningcited by 250
  2. 2023Self-supervised learning of Split Invariant Equivariant representationscited by 44
  3. 2022The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetrycited by 33
  4. 2023Latent Space Symmetry Discoverycited by 29
  5. 2023Steerers: A framework for rotation equivariant keypoint descriptorscited by 21
  6. 2022Back to the Manifold: Recovering from Out-of-Distribution Statescited by 20
  7. 2023A General Theory of Correct, Incorrect, and Extrinsic Equivariancecited by 19
  8. 2023Topological Obstructions and How to Avoid Themcited by 4
  9. 2023Algebras of actions in an agent's representations of the worldcited by 2
  10. 2024CFASL: Composite Factor-Aligned Symmetry Learning for Disentanglement in Variational AutoEncodercited by 2
  11. 2025RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalizationcited by 1
  12. 2026Soft Equivariance Regularization for Invariant Self-Supervised Learningcited by 1
5 more
  1. 2023Equivariant Representation Learning in the Presence of Stabilizerscited by 0
  2. 2023Learning Geometric Representations of Objects via Interactioncited by 0
  3. 2025EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networkscited by 0
  4. 2026Group-invariant Coresets for Data-efficient Active Learningcited by 0
  5. 2026Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learningcited by 0