mlsanityData to 14 Oct 2026

Hardness-Aware Deep Metric Learning

arXiv 1903.05503 ↗First posted 13 Mar 2019cs.CV cs.LGcited by 55

Not on the map. Why?

Abstract (arXiv)

This paper presents a hardness-aware deep metric learning (HDML) framework. Most previous deep metric learning methods employ the hard negative mining strategy to alleviate the lack of informative samples for training. However, this mining strategy only utilizes a subset of training data, which may not be enough to characterize the global geometry of the embedding space comprehensively. To address this problem, we perform linear interpolation on embeddings to adaptively manipulate their hard levels and generate corresponding label-preserving synthetics for recycled training, so that information buried in all samples can be fully exploited and the metric is always challenged with proper difficulty. Our method achieves very competitive performance on the widely used CUB-200-2011, Cars196, and Stanford Online Products datasets.

Key facts. Cited by 55 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 21; 2023: 6; 2024: 7; 2025: 2; 2026: 1.

55 papers.

Sort:

By area:

  1. 2021Topology-Imbalance Learning for Semi-Supervised Node Classificationcited by 56
  2. 2021A Primer on Pretrained Multilingual Language Modelscited by 49
  3. 2021Recall@k Surrogate Loss with Large Batches and Similarity Mixupcited by 49
  4. 2023Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentationcited by 34
  5. 2022Non-isotropy Regularization for Proxy-based Deep Metric Learningcited by 33
  6. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 31
  7. 2021Towards Interpretable Deep Metric Learning with Structural Matchingcited by 30
  8. 2021It Takes Two to Tango: Mixup for Deep Metric Learningcited by 23
  9. 2021Deep Relational Metric Learningcited by 22
  10. 2021Learning with Memory-based Virtual Classes for Deep Metric Learningcited by 21
  11. 2022Integrating Language Guidance into Vision-based Deep Metric Learningcited by 19
  12. 2022A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learningcited by 19
38 more
  1. 2021Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learningcited by 17
  2. 2021Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learningcited by 17
  3. 2022Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translationcited by 13
  4. 2022Attributable Visual Similarity Learningcited by 12
  5. 2022Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learningcited by 11
  6. 2021Cooperative Training and Latent Space Data Augmentation for Robust Medical Image Segmentationcited by 9
  7. 2024Improved Diversity-Promoting Collaborative Metric Learning for Recommendationcited by 9
  8. 2022Contrastive Bayesian Analysis for Deep Metric Learningcited by 8
  9. 2021LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learningcited by 7
  10. 2023Introspective Deep Metric Learningcited by 7
  11. 2022Efficient Malware Analysis Using Metric Embeddingscited by 6
  12. 2021Improving Deep Metric Learning by Divide and Conquercited by 5
  13. 2022DAS: Densely-Anchored Sampling for Deep Metric Learningcited by 5
  14. 2024Globally Correlation-Aware Hard Negative Generationcited by 5
  15. 2021Exploring Adversarial Robustness of Deep Metric Learningcited by 4
  16. 2023Pairwise Similarity Learning is SimPLEcited by 4
  17. 2024Anchor-aware Deep Metric Learning for Audio-visual Retrievalcited by 4
  18. 2024From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learningcited by 4
  19. 2021Instance Similarity Learning for Unsupervised Feature Representationcited by 3
  20. 2022Adaptive neighborhood Metric learningcited by 3
  21. 2022Deep Metric Learning with Chance Constraintscited by 3
  22. 2023Histopathology Image Classification using Deep Manifold Contrastive Learningcited by 3
  23. 2025Metric Learning with Progressive Self-Distillation for Audio-Visual Embedding Learningcited by 3
  24. 2021Rethinking Interactive Image Segmentation: Feature Space Annotationcited by 2
  25. 2021Rank-Consistency Deep Hashing for Scalable Multi-Label Image Searchcited by 2
  26. 2021A Framework to Enhance Generalization of Deep Metric Learning methods using General Discriminative Feature Learning and Class Adversarial Neural Networkscited by 2
  27. 2021Construct Informative Triplet with Two-stage Hard-sample Generationcited by 2
  28. 2022Probabilistic Deep Metric Learning for Hyperspectral Image Classificationcited by 2
  29. 2022Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learningcited by 2
  30. 2023RC3: Regularized Contrastive Cross-lingual Cross-modal Pre-trainingcited by 2
  31. 2024Relational Representation Learning Network for Cross-Spectral Image Patch Matchingcited by 2
  32. 2024Why and How: Knowledge-Guided Learning for Cross-Spectral Image Patch Matchingcited by 2
  33. 2022Learning to Generate Novel Classes for Deep Metric Learningcited by 1
  34. 2022Informative Sample-Aware Proxy for Deep Metric Learningcited by 1
  35. 2024Enhancing Contrastive Learning with Efficient Combinatorial Positive Pairingcited by 1
  36. 2022Indicative Image Retrieval: Turning Blackbox Learning into Greycited by 0
  37. 2022Introspective Deep Metric Learning for Image Retrievalcited by 0
  38. 2022Learning Deep Optimal Embeddings with Sinkhorn Divergencescited by 0

50 most cited of 55 All 55 (JSON)