mlsanityData to 14 Oct 2026

DUET: 2D Structured and Approximately Equivariant Representations

arXiv 2306.16058 ↗First posted 28 Jun 2023cs.LG cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Multiview Self-Supervised Learning (MSSL) is based on learning invariances with respect to a set of input transformations. However, invariance partially or totally removes transformation-related information from the representations, which might harm performance for specific downstream tasks that require such information. We propose 2D strUctured and EquivarianT representations (coined DUET), which are 2d representations organized in a matrix structure, and equivariant with respect to transformations acting on the input data. DUET representations maintain information about an input transformation, while remaining semantically expressive. Compared to SimCLR (Chen et al., 2020) (unstructured and invariant) and ESSL (Dangovski et al., 2022) (unstructured and equivariant), the structured and equivariant nature of DUET representations enables controlled generation with lower reconstruction error, while controllability is not possible with SimCLR or ESSL. DUET also achieves higher accuracy for several discriminative tasks, and improves transfer learning.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 34 of its 44 references that are in the map. First posted on arXiv 28 Jun 2023.

Builds on

34 of 44 references.

References · 34

  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. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  7. 2013Auto-Encoding Variational Bayescited by 4,053
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  9. 2013Describing Textures in the Wildcited by 2,125
  10. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  11. 2018Group Normalizationcited by 1,524
  12. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
22 more
  1. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  2. 2016Group Equivariant Convolutional Networkscited by 1,165
  3. 2020What Makes for Good Views for Contrastive Learning?cited by 846
  4. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 734
  5. 2019On Mutual Information Maximization for Representation Learningcited by 316
  6. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 241
  7. 2021Contrastive Learning Inverts the Data Generating Processcited by 221
  8. 2019Scale-Equivariant Steerable Networkscited by 110
  9. 2019Putting An End to End-to-End: Gradient-Isolated Learning of Representationscited by 86
  10. 2016TI-POOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networkscited by 67
  11. 2021Equivariant Contrastive Learningcited by 66
  12. 2018Explorations in Homeomorphic Variational Auto-Encodingcited by 65
  13. 2021Improving Transferability of Representations via Augmentation-Aware Self-Supervisioncited by 49
  14. 2021Enabling equivariance for arbitrary Lie groupscited by 22
  15. 2020Addressing Feature Suppression in Unsupervised Visual Representationscited by 13
  16. 2019Independent Subspace Analysis for Unsupervised Learning of Disentangled Representationscited by 8
  17. 2021Hybrid Generative-Contrastive Representation Learningcited by 8
  18. 2023MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priorscited by 8
  19. 2022Offset equivariant networks and their applicationscited by 6
  20. 2022Homomorphic Self-Supervised Learningcited by 3
  21. 2018Non-Parametric Transformation Networkscited by 2
  22. 2021Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networkscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2023Approximately Equivariant Graph Networkscited by 16
  2. 2024Tensor learning with orthogonal, Lorentz, and symplectic symmetriescited by 3