mlsanityData to 14 Oct 2026

Hyp-UML: Hyperbolic Image Retrieval with Uncertainty-aware Metric Learning

arXiv 2310.08390 ↗First posted 12 Oct 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Metric learning plays a critical role in training image retrieval and classification. It is also a key algorithm in representation learning, e.g., for feature learning and its alignment in metric space. Hyperbolic embedding has been recently developed. Compared to the conventional Euclidean embedding in most of the previously developed models, Hyperbolic embedding can be more effective in representing the hierarchical data structure. Second, uncertainty estimation/measurement is a long-lasting challenge in artificial intelligence. Successful uncertainty estimation can improve a machine learning model's performance, robustness, and security. In Hyperbolic space, uncertainty measurement is at least with equivalent, if not more, critical importance. In this paper, we develop a Hyperbolic image embedding with uncertainty-aware metric learning for image retrieval. We call our method Hyp-UML: Hyperbolic Uncertainty-aware Metric Learning. Our contribution are threefold: we propose an image embedding algorithm based on Hyperbolic space, with their corresponding uncertainty value; we propose two types of uncertainty-aware metric learning, for the popular Contrastive learning and conventional margin-based metric learning, respectively. We perform extensive experimental validations to prove that the proposed algorithm can achieve state-of-the-art results among related methods. The comprehensive ablation study validates the effectiveness of each component of the proposed algorithm.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 30 of its 52 references that are in the map. First posted on arXiv 12 Oct 2023.

Builds on

30 of 52 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  3. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  4. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
  5. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  6. 2018Hyperbolic Neural Networkscited by 402
  7. 2020Understanding the Behaviour of Contrastive Losscited by 398
  8. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  9. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 338
  10. 2020A Metric Learning Reality Checkcited by 321
  11. 2017Sampling Matters in Deep Embedding Learningcited by 285
  12. 2019Hyperbolic Image Embeddingscited by 221
18 more
  1. 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
  2. 2021Hyperbolic Deep Neural Networks: A Surveycited by 139
  3. 2019Cross-Batch Memory for Embedding Learningcited by 132
  4. 2018Hyperbolic Attention Networkscited by 122
  5. 2022Hyperbolic Vision Transformers: Combining Improvements in Metric Learningcited by 111
  6. 2021Training Vision Transformers for Image Retrievalcited by 90
  7. 2019Ranked List Loss for Deep Metric Learningcited by 77
  8. 2021Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifierscited by 57
  9. 2021HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projectionscited by 47
  10. 2017Deep Representation Learning with Part Loss for Person Re-Identificationcited by 44
  11. 2019MIC: Mining Interclass Characteristics for Improved Metric Learningcited by 41
  12. 2022Hyperbolic Graph Neural Networks: A Review of Methods and Applicationscited by 40
  13. 2020Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibrationcited by 34
  14. 2021AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantificationcited by 31
  15. 2021CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Datacited by 28
  16. 2018Adversarial Distillation of Bayesian Neural Network Posteriorscited by 27
  17. 2021Temperature as Uncertainty in Contrastive Learningcited by 25
  18. 2021ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Networkcited by 25

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2026Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Modelscited by 2
  2. 2025A Set-to-Set Distance Measure in Hyperbolic Spacecited by 0
  3. 2026HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understandingcited by 0