mlsanityData to 7 Oct 2026

A Metric Learning Reality Check

arXiv 2003.08505 ↗First posted 18 Mar 2020cs.CVcited by 317

Not on the map. Why?

Abstract (arXiv)

Deep metric learning papers from the past four years have consistently claimed great advances in accuracy, often more than doubling the performance of decade-old methods. In this paper, we take a closer look at the field to see if this is actually true. We find flaws in the experimental methodology of numerous metric learning papers, and show that the actual improvements over time have been marginal at best.

Key facts. Cited by 317 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 78; 2022: 87; 2023: 63; 2024: 29; 2025: 25; 2026: 35.

317 papers.

Sort:

By area:

  1. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  2. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  3. 2021True Few-Shot Learning with Language Modelscited by 343
  4. 2021CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Taskscited by 199
  5. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 199
  6. 2021Accounting for Variance in Machine Learning Benchmarkscited by 195
  7. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  8. 2023Optimal Transport Aggregation for Visual Place Recognitioncited by 151
  9. 2021Probabilistic Embeddings for Cross-Modal Retrievalcited by 150
  10. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  11. 2021The Benchmark Lotterycited by 133
  12. 2022What to Hide from Your Students: Attention-Guided Masked Image Modelingcited by 117
38 more
  1. 2022Hyperbolic Vision Transformers: Combining Improvements in Metric Learningcited by 109
  2. 2021Training Vision Transformers for Image Retrievalcited by 90
  3. 2025A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibilitycited by 89
  4. 2022OpenGait: Revisiting Gait Recognition Toward Better Practicalitycited by 85
  5. 2023CompoDiff: Versatile Composed Image Retrieval With Latent Diffusioncited by 84
  6. 2022ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similaritycited by 82
  7. 2024Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvementscited by 82
  8. 2022Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Countingcited by 80
  9. 2022Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddingscited by 75
  10. 2021Deep Learning for Instance Retrieval: A Surveycited by 70
  11. 2022Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Frameworkcited by 59
  12. 2021Recall@k Surrogate Loss with Large Batches and Similarity Mixupcited by 49
  13. 2023WildlifeDatasets: An open-source toolkit for animal re-identificationcited by 49
  14. 2021On Semantic Similarity in Video Retrievalcited by 45
  15. 2021Rethinking "Batch" in BatchNormcited by 44
  16. 2022Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Trainingcited by 44
  17. 2021von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learningcited by 42
  18. 2021Reducing Label Effort: Self-Supervised meets Active Learningcited by 42
  19. 2021A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectivescited by 41
  20. 2021MinkLoc++: Lidar and Monocular Image Fusion for Place Recognitioncited by 41
  21. 2023Improved Probabilistic Image-Text Representationscited by 40
  22. 2021How I failed machine learning in medical imaging -- shortcomings and recommendationscited by 37
  23. 2022ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCOcited by 37
  24. 2023Unicom: Universal and Compact Representation Learning for Image Retrievalcited by 36
  25. 2023Exposing and Mitigating Spurious Correlations for Cross-Modal Retrievalcited by 35
  26. 2021Learning Intra-Batch Connections for Deep Metric Learningcited by 34
  27. 2022Non-isotropy Regularization for Proxy-based Deep Metric Learningcited by 33
  28. 2021Towards Interpretable Deep Metric Learning with Structural Matchingcited by 30
  29. 2021TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fieldscited by 29
  30. 2022Probabilistic Compositional Embeddings for Multimodal Image Retrievalcited by 29
  31. 2023Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representationscited by 28
  32. 2023Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matterscited by 27
  33. 2023Language-only Efficient Training of Zero-shot Composed Image Retrievalcited by 27
  34. 2024Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognitioncited by 27
  35. 2021Learning with Holographic Reduced Representationscited by 25
  36. 2021ConvFiT: Conversational Fine-Tuning of Pretrained Language Modelscited by 25
  37. 2021EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scalecited by 25
  38. 2021A Deep Metric Learning Approach to Account Linkingcited by 24

50 most cited of 317 All 317 (JSON)