mlsanityData to 14 Oct 2026

Leveraging Hidden Structure in Self-Supervised Learning

arXiv 2106.16060 ↗First posted 30 Jun 2021cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This work considers the problem of learning structured representations from raw images using self-supervised learning. We propose a principled framework based on a mutual information objective, which integrates self-supervised and structure learning. Furthermore, we devise a post-hoc procedure to interpret the meaning of the learnt representations. Preliminary experiments on CIFAR-10 show that the proposed framework achieves higher generalization performance in downstream classification tasks and provides more interpretable representations compared to the ones learnt through traditional self-supervised learning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 47 references that are in the map. First posted on arXiv 30 Jun 2021.

Builds on

37 of 47 references.

References · 37

  1. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  4. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  5. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  6. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  7. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  8. 2016Variational Graph Auto-Encoderscited by 1,382
  9. 2019Contrastive Multiview Codingcited by 1,301
  10. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  11. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  12. 2016Colorful Image Colorizationcited by 1,114
25 more
  1. 2018Deep Graph Infomaxcited by 1,106
  2. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
  3. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  4. 2020Object-Centric Learning with Slot Attentioncited by 876
  5. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 734
  6. 2018MINE: Mutual Information Neural Estimationcited by 683
  7. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 673
  8. 2019On Variational Bounds of Mutual Informationcited by 559
  9. 2018Neural Relational Inference for Interacting Systemscited by 339
  10. 2019On Mutual Information Maximization for Representation Learningcited by 316
  11. 2014Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networkscited by 300
  12. 2016Learning Representations for Automatic Colorizationcited by 251
  13. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  14. 2019Recurrent Independent Mechanismscited by 219
  15. 2016Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Predictioncited by 217
  16. 2018Hyperspherical Variational Auto-Encoderscited by 189
  17. 2018Formal Limitations on the Measurement of Mutual Informationcited by 189
  18. 2019Understanding the Limitations of Variational Mutual Information Estimatorscited by 140
  19. 2017Neural Expectation Maximizationcited by 123
  20. 2017Representation Learning by Learning to Countcited by 120
  21. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  22. 2018Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactionscited by 100
  23. 2018Self-Supervised Feature Learning by Learning to Spot Artifactscited by 43
  24. 2020Self-Supervised Relational Reasoning for Representation Learningcited by 37
  25. 2020Hierarchical Relational Inferencecited by 9

Built on by

Not cited yet.