mlsanityData to 7 Oct 2026

Hyperbolic Contrastive Learning

arXiv 2302.01409 ↗First posted 2 Feb 2023cs.CV cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Learning good image representations that are beneficial to downstream tasks is a challenging task in computer vision. As such, a wide variety of self-supervised learning approaches have been proposed. Among them, contrastive learning has shown competitive performance on several benchmark datasets. The embeddings of contrastive learning are arranged on a hypersphere that results in using the inner (dot) product as a distance measurement in Euclidean space. However, the underlying structure of many scientific fields like social networks, brain imaging, and computer graphics data exhibit highly non-Euclidean latent geometry. We propose a novel contrastive learning framework to learn semantic relationships in the hyperbolic space. Hyperbolic space is a continuous version of trees that naturally owns the ability to model hierarchical structures and is thus beneficial for efficient contrastive representation learning. We also extend the proposed Hyperbolic Contrastive Learning (HCL) to the supervised domain and studied the adversarial robustness of HCL. The comprehensive experiments show that our proposed method achieves better results on self-supervised pretraining, supervised classification, and higher robust accuracy than baseline methods.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 67 of its 91 references that are in the map. First posted on arXiv 2 Feb 2023.

Builds on

67 of 91 references.

References · 67

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  8. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  9. 2017Mask R-CNNcited by 7,259
  10. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  11. 2013Intriguing properties of neural networkscited by 5,114
  12. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
38 more
  1. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  2. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  3. 2020Supervised Contrastive Learningcited by 2,803
  4. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  5. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  6. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  7. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  10. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  11. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  12. 2019Contrastive Multiview Codingcited by 1,297
  13. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  14. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  15. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  16. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
  17. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  18. 2016Universal adversarial perturbationscited by 774
  19. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  20. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  21. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 636
  22. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  23. 2020A Survey on Contrastive Self-supervised Learningcited by 553
  24. 2019A Theoretical Analysis of Contrastive Unsupervised Representation Learningcited by 530
  25. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  26. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  27. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  28. 2020Understanding the Behaviour of Contrastive Losscited by 397
  29. 2018Hyperbolic Neural Networkscited by 393
  30. 2019Making Convolutional Networks Shift-Invariant Againcited by 390
  31. 2020A Metric Learning Reality Checkcited by 317
  32. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 261
  33. 2019Unsupervised Embedding Learning via Invariant and Spreading Instance Featurecited by 231
  34. 2019Hyperbolic Image Embeddingscited by 219
  35. 2019Are Labels Required for Improving Adversarial Robustness?cited by 162
  36. 2020Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuningcited by 152
  37. 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
  38. 2019Adversarial Robustness through Local Linearizationcited by 146

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 7; 2025: 4; 2026: 1.

15 papers.

Sort:

By area:

  1. 2023Hyperbolic Deep Learning in Computer Vision: A Surveycited by 72
  2. 2025HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Expertscited by 22
  3. 2024Learning Structured Representations with Hyperbolic Embeddingscited by 16
  4. 2023Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detectioncited by 14
  5. 2024Understanding Hyperbolic Metric Learning through Hard Negative Samplingcited by 10
  6. 2026GeoWorld: Geometric World Modelscited by 6
  7. 2023HMSN: Hyperbolic Self-Supervised Learning by Clustering with Ideal Prototypescited by 5
  8. 2024A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasetscited by 4
  9. 2025Continual Hyperbolic Learning of Instances and Classescited by 4
  10. 2024Leveraging Superfluous Information in Contrastive Representation Learningcited by 3
  11. 2024Hyperbolic Chamfer Distance for Point Cloud Completion and Beyondcited by 3
  12. 2024Hgformer: Hyperbolic Graph Transformer for Recommendationcited by 2
3 more
  1. 2025Predicate Hierarchies Improve Few-Shot State Classificationcited by 1
  2. 2025A Mathematical Perspective On Contrastive Learningcited by 1
  3. 2024Siamese networks for Poincar'e embeddings and the reconstruction of evolutionary treescited by 0