mlsanityData to 7 Oct 2026

Hyperbolic Vision Transformers: Combining Improvements in Metric Learning

arXiv 2203.10833 ↗First posted 21 Mar 2022cs.CV cs.LGcited by 109

Not on the map. Why?

Abstract (arXiv)

Metric learning aims to learn a highly discriminative model encouraging the embeddings of similar classes to be close in the chosen metrics and pushed apart for dissimilar ones. The common recipe is to use an encoder to extract embeddings and a distance-based loss function to match the representations -- usually, the Euclidean distance is utilized. An emerging interest in learning hyperbolic data embeddings suggests that hyperbolic geometry can be beneficial for natural data. Following this line of work, we propose a new hyperbolic-based model for metric learning. At the core of our method is a vision transformer with output embeddings mapped to hyperbolic space. These embeddings are directly optimized using modified pairwise cross-entropy loss. We evaluate the proposed model with six different formulations on four datasets achieving the new state-of-the-art performance. The source code is available at https://github.com/htdt/hyp_metric.

Key facts. Cited by 109 papers in the map (data through 7 Oct 2026). Builds on 45 of its 69 references that are in the map. First posted on arXiv 21 Mar 2022.

Builds on

45 of 69 references.

References · 45

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  7. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  8. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  9. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  10. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  11. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  12. 2014Going Deeper with Convolutionscited by 4,231
33 more
  1. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  2. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  3. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  4. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  5. 2013Exact solutions to the nonlinear dynamics of learning in deep linear neural networkscited by 748
  6. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  7. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  8. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  9. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 562
  10. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  11. 2018Hyperbolic Neural Networkscited by 393
  12. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  13. 2020A Metric Learning Reality Checkcited by 317
  14. 2017Sampling Matters in Deep Embedding Learningcited by 285
  15. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 261
  16. 2017No Fuss Distance Metric Learning using Proxiescited by 225
  17. 2019Hyperbolic Image Embeddingscited by 219
  18. 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
  19. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
  20. 2017Beyond triplet loss: a deep quadruplet network for person re-identificationcited by 172
  21. 2019SoftTriple Loss: Deep Metric Learning Without Triplet Samplingcited by 163
  22. 2021Pretrained Transformers as Universal Computation Enginescited by 162
  23. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  24. 2019Cross-Batch Memory for Embedding Learningcited by 130
  25. 2018Deep Metric Learning with Hierarchical Triplet Losscited by 112
  26. 2020ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysiscited by 107
  27. 2020A unifying mutual information view of metric learning: cross-entropy vs. pairwise lossescited by 100
  28. 2021Training Vision Transformers for Image Retrievalcited by 90
  29. 2019Transductive Episodic-Wise Adaptive Metric for Few-Shot Learningcited by 67
  30. 2018Attention-based Ensemble for Deep Metric Learningcited by 56
  31. 2019MIC: Mining Interclass Characteristics for Improved Metric Learningcited by 41
  32. 2018Deep Metric Learning with BIER: Boosting Independent Embeddings Robustlycited by 40
  33. 2019Metric Learning With HORDE: High-Order Regularizer for Deep Embeddingscited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 23; 2024: 27; 2025: 32; 2026: 21.

109 papers.

Sort:

By area:

  1. 2023Hyperbolic Image-Text Representationscited by 132
  2. 2023Hyperbolic Deep Learning in Computer Vision: A Surveycited by 72
  3. 2023E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuningcited by 70
  4. 2023Fully Hyperbolic Convolutional Neural Networks for Computer Visioncited by 48
  5. 2023HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representationscited by 42
  6. 2024Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Spacecited by 39
  7. 2023Unicom: Universal and Compact Representation Learning for Image Retrievalcited by 36
  8. 2022HIER: Metric Learning Beyond Class Labels via Hierarchical Regularizationcited by 26
  9. 2023Poincar'e ResNetcited by 24
  10. 2023HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusioncited by 24
  11. 2025Hyperbolic Category Discoverycited by 20
  12. 2025Hyperbolic Deep Learning for Foundation Models: A Surveycited by 20
38 more
  1. 2024Emergent Visual-Semantic Hierarchies in Image-Text Representationscited by 19
  2. 2022Rethinking the compositionality of point clouds through regularization in the hyperbolic spacecited by 18
  3. 2023Hyperbolic Active Learning for Semantic Segmentation under Domain Shiftcited by 18
  4. 2024HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Textscited by 17
  5. 2024Lorentzian Residual Neural Networkscited by 17
  6. 2025Hyperbolic Safety-Aware Vision-Language Modelscited by 17
  7. 2025DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformerscited by 17
  8. 2025HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic Learningcited by 17
  9. 2024Learning Structured Representations with Hyperbolic Embeddingscited by 16
  10. 2023Hyperbolic Contrastive Learningcited by 15
  11. 2023Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detectioncited by 14
  12. 2025HyperCore: The Core Framework for Building Hyperbolic Foundation Models with Comprehensive Modulescited by 12
  13. 2024Improving Visual Recognition with Hyperbolical Visual Hierarchy Mappingcited by 11
  14. 2024Understanding Hyperbolic Metric Learning through Hard Negative Samplingcited by 10
  15. 2024Hyperbolic Learning with Multimodal Large Language Modelscited by 10
  16. 2022Hyperbolic Hierarchical Contrastive Hashingcited by 9
  17. 2024Towards Improved Proxy-based Deep Metric Learning via Data-Augmented Domain Adaptationcited by 9
  18. 2024Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincar'e Ballcited by 9
  19. 2023HyperFed: Hyperbolic Prototypes Exploration with Consistent Aggregation for Non-IID Data in Federated Learningcited by 8
  20. 2024HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generationcited by 8
  21. 2024UDON: Universal Dynamic Online distillatioN for generic image representationscited by 8
  22. 2024HVT: A Comprehensive Vision Framework for Learning in Non-Euclidean Spacecited by 8
  23. 2023HypLL: The Hyperbolic Learning Librarycited by 6
  24. 2024Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learningcited by 6
  25. 2024DVF: Advancing Robust and Accurate Fine-Grained Image Retrieval with Retrieval Guidelinescited by 6
  26. 2022Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimizationcited by 5
  27. 2023HMSN: Hyperbolic Self-Supervised Learning by Clustering with Ideal Prototypescited by 5
  28. 2023Hyperbolic Geometry in Computer Vision: A Surveycited by 4
  29. 2024A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasetscited by 4
  30. 2024Anchor-aware Deep Metric Learning for Audio-visual Retrievalcited by 4
  31. 2024Robust Hyperbolic Learning with Curvature-Aware Optimizationcited by 4
  32. 2024Potential Field Based Deep Metric Learningcited by 4
  33. 2025HyLiFormer: Hyperbolic Linear Attention for Skeleton-based Human Action Recognitioncited by 4
  34. 2023Hyp-UML: Hyperbolic Image Retrieval with Uncertainty-aware Metric Learningcited by 3
  35. 2024Hyp-OC: Hyperbolic One Class Classification for Face Anti-Spoofingcited by 3
  36. 2024Learning Multi-Manifold Embedding for Out-Of-Distribution Detectioncited by 3
  37. 2024Hyperbolic Image-and-Pointcloud Contrastive Learning for 3D Classificationcited by 3
  38. 2024Klein Model for Hyperbolic Neural Networkscited by 3

50 most cited of 109 All 109 (JSON)