mlsanityData to 14 Oct 2026

In Defense of the Triplet Loss for Person Re-Identification

arXiv 1703.07737 ↗First posted 22 Mar 2017cs.CV cs.NEcited by 786

Not on the map. Why?

Abstract (arXiv)

In the past few years, the field of computer vision has gone through a revolution fueled mainly by the advent of large datasets and the adoption of deep convolutional neural networks for end-to-end learning. The person re-identification subfield is no exception to this. Unfortunately, a prevailing belief in the community seems to be that the triplet loss is inferior to using surrogate losses (classification, verification) followed by a separate metric learning step. We show that, for models trained from scratch as well as pretrained ones, using a variant of the triplet loss to perform end-to-end deep metric learning outperforms most other published methods by a large margin.

Key facts. Cited by 786 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 223; 2022: 163; 2023: 133; 2024: 119; 2025: 74; 2026: 74.

786 papers.

Sort:

By area:

  1. 2021Deep Long-Tailed Learning: A Surveycited by 417
  2. 2021Motion Representations for Articulated Animationcited by 255
  3. 2021A Survey on Deep Semi-supervised Learningcited by 251
  4. 2021Contrastive Learning for Compact Single Image Dehazingcited by 219
  5. 2022Thin-Plate Spline Motion Model for Image Animationcited by 210
  6. 2022CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labelscited by 181
  7. 2021Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detectioncited by 134
  8. 2021Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformercited by 120
  9. 2022Gait Recognition in the Wild with Dense 3D Representations and A Benchmarkcited by 114
  10. 2022Clothes-Changing Person Re-identification with RGB Modality Onlycited by 98
  11. 2022GSV-Cities: Toward Appropriate Supervised Visual Place Recognitioncited by 93
  12. 2021Cluster Contrast for Unsupervised Person Re-Identificationcited by 89
38 more
  1. 2021Monocular Quasi-Dense 3D Object Trackingcited by 81
  2. 2023Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identificationcited by 79
  3. 2021Generalizable Person Re-identification with Relevance-aware Mixture of Expertscited by 77
  4. 2021ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesiscited by 76
  5. 2021Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularizationcited by 69
  6. 2021ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identificationcited by 69
  7. 2021Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondencescited by 66
  8. 2021Deep Learning for Face Anti-Spoofing: A Surveycited by 65
  9. 2022DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformerscited by 65
  10. 2022Body Part-Based Representation Learning for Occluded Person Re-Identificationcited by 64
  11. 2022Nested Collaborative Learning for Long-Tailed Visual Recognitioncited by 63
  12. 2021Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Searchcited by 62
  13. 2021SiamMOT: Siamese Multi-Object Trackingcited by 62
  14. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  15. 2023Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classificationcited by 60
  16. 2022Part-based Pseudo Label Refinement for Unsupervised Person Re-identificationcited by 59
  17. 2024A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Modelcited by 59
  18. 2021GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Setcited by 57
  19. 2021Lifelong Person Re-Identification via Adaptive Knowledge Accumulationcited by 57
  20. 2022NFormer: Robust Person Re-identification with Neighbor Transformercited by 57
  21. 2021Person Re-identification Method Based on Color Attack and Joint Defencecited by 56
  22. 2022Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networkscited by 55
  23. 2022Audio-Driven Co-Speech Gesture Video Generationcited by 55
  24. 2021Deep Gait Recognition: A Surveycited by 54
  25. 2021Intra-Inter Camera Similarity for Unsupervised Person Re-Identificationcited by 52
  26. 2022Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCocited by 52
  27. 2021Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNscited by 51
  28. 2021IDM: An Intermediate Domain Module for Domain Adaptive Person Re-IDcited by 51
  29. 2021GiT: Graph Interactive Transformer for Vehicle Re-identificationcited by 49
  30. 2021Towards Robust Bisimulation Metric Learningcited by 49
  31. 2023PLIP: Language-Image Pre-training for Person Representation Learningcited by 49
  32. 2023WildlifeDatasets: An open-source toolkit for animal re-identificationcited by 49
  33. 2021AAformer: Auto-Aligned Transformer for Person Re-Identificationcited by 48
  34. 2022GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021cited by 46
  35. 2023Exploring Deep Models for Practical Gait Recognitioncited by 46
  36. 2022Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Trainingcited by 45
  37. 2022Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularizationcited by 45
  38. 2024Cross-Modality Perturbation Synergy Attack for Person Re-identificationcited by 45

50 most cited of 786 All 786 (JSON)