mlsanityData to 7 Oct 2026

Sampling Matters in Deep Embedding Learning

arXiv 1706.07567 ↗First posted 23 Jun 2017cs.CVcited by 285

Not on the map. Why?

Abstract (arXiv)

Deep embeddings answer one simple question: How similar are two images? Learning these embeddings is the bedrock of verification, zero-shot learning, and visual search. The most prominent approaches optimize a deep convolutional network with a suitable loss function, such as contrastive loss or triplet loss. While a rich line of work focuses solely on the loss functions, we show in this paper that selecting training examples plays an equally important role. We propose distance weighted sampling, which selects more informative and stable examples than traditional approaches. In addition, we show that a simple margin based loss is sufficient to outperform all other loss functions. We evaluate our approach on the Stanford Online Products, CAR196, and the CUB200-2011 datasets for image retrieval and clustering, and on the LFW dataset for face verification. Our method achieves state-of-the-art performance on all of them.

Key facts. Cited by 285 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 81; 2022: 81; 2023: 51; 2024: 32; 2025: 22; 2026: 18.

285 papers.

Sort:

By area:

  1. 2022When and why vision-language models behave like bags-of-words, and what to do about it?cited by 603
  2. 2022Hyperbolic Vision Transformers: Combining Improvements in Metric Learningcited by 109
  3. 2023Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisationcited by 107
  4. 2021Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformerscited by 93
  5. 2022GSV-Cities: Toward Appropriate Supervised Visual Place Recognitioncited by 92
  6. 2021Training Vision Transformers for Image Retrievalcited by 90
  7. 2021Cluster Contrast for Unsupervised Person Re-Identificationcited by 89
  8. 2023Verbs in Action: Improving verb understanding in video-language modelscited by 76
  9. 2022Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddingscited by 75
  10. 2022Audio Self-supervised Learning: A Surveycited by 65
  11. 2021Instance-level Image Retrieval using Reranking Transformerscited by 63
  12. 2024Yo'LLaVA: Your Personalized Language and Vision Assistantcited by 61
38 more
  1. 2022Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Frameworkcited by 59
  2. 2022Visual Recognition with Deep Nearest Centroidscited by 59
  3. 2021Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuningcited by 50
  4. 2021Recall@k Surrogate Loss with Large Batches and Similarity Mixupcited by 49
  5. 2021Towards Robust Bisimulation Metric Learningcited by 49
  6. 2021Incremental False Negative Detection for Contrastive Learningcited by 48
  7. 2022LocVTP: Video-Text Pre-training for Temporal Localizationcited by 44
  8. 2021von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learningcited by 42
  9. 2021SphereFace2: Binary Classification is All You Need for Deep Face Recognitioncited by 42
  10. 2021Towards Unsupervised Domain Generalizationcited by 40
  11. 2023Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understandingcited by 40
  12. 2023SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understandingcited by 38
  13. 2023SAMAug: Point Prompt Augmentation for Segment Anything Modelcited by 38
  14. 2021Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identificationcited by 37
  15. 2023Simple, Effective and General: A New Backbone for Cross-view Image Geo-localizationcited by 36
  16. 2021Learning Intra-Batch Connections for Deep Metric Learningcited by 34
  17. 2022Non-isotropy Regularization for Proxy-based Deep Metric Learningcited by 33
  18. 2024Data curation via joint example selection further accelerates multimodal learningcited by 32
  19. 2021Pairwise Supervised Contrastive Learning of Sentence Representationscited by 31
  20. 2021Towards Interpretable Deep Metric Learning with Structural Matchingcited by 30
  21. 2021VS-Net: Voting with Segmentation for Visual Localizationcited by 29
  22. 2021TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fieldscited by 29
  23. 2022From t-SNE to UMAP with contrastive learningcited by 28
  24. 2022Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Datacited by 27
  25. 2024Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognitioncited by 27
  26. 2021Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representationscited by 24
  27. 2022OutfitTransformer: Learning Outfit Representations for Fashion Recommendationcited by 24
  28. 2021Noise-resistant Deep Metric Learning with Ranking-based Instance Selectioncited by 23
  29. 2021It Takes Two to Tango: Mixup for Deep Metric Learningcited by 23
  30. 2021SphereFace Revived: Unifying Hyperspherical Face Recognitioncited by 23
  31. 2021Pairwise Learning for Neural Link Predictioncited by 23
  32. 2021Deep Relational Metric Learningcited by 22
  33. 2021Embedding Transfer with Label Relaxation for Improved Metric Learningcited by 21
  34. 2022COCOA: Cross Modality Contrastive Learning for Sensor Datacited by 21
  35. 2023Internet Explorer: Targeted Representation Learning on the Open Webcited by 21
  36. 2021TypeNet: Deep Learning Keystroke Biometricscited by 19
  37. 2021Robust and Decomposable Average Precision for Image Retrievalcited by 19
  38. 2022Integrating Language Guidance into Vision-based Deep Metric Learningcited by 19

50 most cited of 285 All 285 (JSON)