mlsanityData to 7 Oct 2026

Proxy Anchor Loss for Deep Metric Learning

arXiv 2003.13911 ↗First posted 31 Mar 2020cs.CV cs.LGcited by 195

Not on the map. Why?

Abstract (arXiv)

Existing metric learning losses can be categorized into two classes: pair-based and proxy-based losses. The former class can leverage fine-grained semantic relations between data points, but slows convergence in general due to its high training complexity. In contrast, the latter class enables fast and reliable convergence, but cannot consider the rich data-to-data relations. This paper presents a new proxy-based loss that takes advantages of both pair- and proxy-based methods and overcomes their limitations. Thanks to the use of proxies, our loss boosts the speed of convergence and is robust against noisy labels and outliers. At the same time, it allows embedding vectors of data to interact with each other in its gradients to exploit data-to-data relations. Our method is evaluated on four public benchmarks, where a standard network trained with our loss achieves state-of-the-art performance and most quickly converges.

Key facts. Cited by 195 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 37; 2022: 50; 2023: 35; 2024: 25; 2025: 28; 2026: 20.

195 papers.

Sort:

By area:

  1. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  2. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  3. 2022Hyperbolic Vision Transformers: Combining Improvements in Metric Learningcited by 109
  4. 2021High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learningcited by 54
  5. 2023GeneCIS: A Benchmark for General Conditional Image Similaritycited by 46
  6. 2022Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Trainingcited by 44
  7. 2021Learning Intra-Batch Connections for Deep Metric Learningcited by 34
  8. 2024SelEx: Self-Expertise in Fine-Grained Generalized Category Discoverycited by 34
  9. 2022Non-isotropy Regularization for Proxy-based Deep Metric Learningcited by 33
  10. 2021Birds of a Feather: Capturing Avian Shape Models from Imagescited by 30
  11. 2021Towards Interpretable Deep Metric Learning with Structural Matchingcited by 30
  12. 2022HIER: Metric Learning Beyond Class Labels via Hierarchical Regularizationcited by 26
38 more
  1. 2021A Deep Metric Learning Approach to Account Linkingcited by 24
  2. 2021Noise-resistant Deep Metric Learning with Ranking-based Instance Selectioncited by 23
  3. 2021It Takes Two to Tango: Mixup for Deep Metric Learningcited by 23
  4. 2021Deep Relational Metric Learningcited by 22
  5. 2021Embedding Transfer with Label Relaxation for Improved Metric Learningcited by 21
  6. 2021Learning with Memory-based Virtual Classes for Deep Metric Learningcited by 21
  7. 2021Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptationcited by 21
  8. 2022Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problemcited by 20
  9. 2022Integrating Language Guidance into Vision-based Deep Metric Learningcited by 19
  10. 2022A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learningcited by 19
  11. 2024Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwardscited by 19
  12. 2021Hierarchical Proxy-based Loss for Deep Metric Learningcited by 18
  13. 2021Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual Stylescited by 18
  14. 2023From Global to Local: Multi-scale Out-of-distribution Detectioncited by 18
  15. 2021Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learningcited by 17
  16. 2021Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learningcited by 17
  17. 2022Continual Learning for Visual Search with Backward Consistent Feature Embeddingcited by 17
  18. 2022Utilizing Expert Features for Contrastive Learning of Time-Series Representationscited by 17
  19. 2025DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformerscited by 17
  20. 2023Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discoverycited by 16
  21. 2024Learning Structured Representations with Hyperbolic Embeddingscited by 16
  22. 2025Fewer Tokens, Greater Scaling: Self-Adaptive Visual Bases for Efficient and Expansive Representation Learningcited by 16
  23. 2022RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrievalcited by 15
  24. 2024Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Surveycited by 15
  25. 2021Bag of Tricks and A Strong baseline for Image Copy Detectioncited by 14
  26. 2021GPR1200: A Benchmark for General-Purpose Content-Based Image Retrievalcited by 14
  27. 2022Self-Taught Metric Learning without Labelscited by 13
  28. 2024Novel Class Discovery for Ultra-Fine-Grained Visual Categorizationcited by 13
  29. 202550 Years of Automated Face Recognitioncited by 13
  30. 2021All the attention you need: Global-local, spatial-channel attention for image retrievalcited by 12
  31. 2022Attributable Visual Similarity Learningcited by 12
  32. 2021ASMR: Learning Attribute-Based Person Search with Adaptive Semantic Margin Regularizercited by 11
  33. 2022Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learningcited by 11
  34. 2023Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable and Trustworthy Image Recognitioncited by 11
  35. 2022Siamese Prototypical Contrastive Learningcited by 10
  36. 2024Understanding Hyperbolic Metric Learning through Hard Negative Samplingcited by 10
  37. 2024Bringing Multimodality to Amazon Visual Search Systemcited by 10
  38. 2025Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generationcited by 10

50 most cited of 195 All 195 (JSON)