mlsanityData to 14 Oct 2026

Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions

arXiv 2109.06057 ↗First posted 1 Sep 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Person re-identification (Re-ID) has been a significant research topic in the past decade due to its real-world applications and research significance. While supervised person Re-ID methods achieve superior performance over unsupervised counterparts, they can not scale to large unlabelled datasets and new domains due to the prohibitive labelling cost. Therefore, unsupervised person Re-ID has drawn increasing attention for its potential to address the scalability issue in person Re-ID. Unsupervised person Re-ID is challenging primarily due to lacking identity labels to supervise person feature learning. The corresponding solutions are diverse and complex, with various merits and limitations. Therefore, comprehensive surveys on this topic are essential to summarise challenges and solutions to foster future research. Existing person Re-ID surveys have focused on supervised methods from classifications and applications but lack detailed discussion on how the person Re-ID solutions address the underlying challenges. This survey review recent works on unsupervised person Re-ID from the perspective of challenges and solutions. Specifically, we provide an in-depth analysis of highly influential methods considering the four significant challenges in unsupervised person Re-ID: 1) lacking ground-truth identity labels to supervise person feature learning; 2) learning discriminative person features with pseudo-supervision; 3) learning cross-camera invariant person feature, and 4) the domain shift between datasets. We summarise and analyse evaluation results and provide insights on the effectiveness of the solutions. Finally, we discuss open issues and suggest some promising future research directions.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 62 of its 123 references that are in the map. First posted on arXiv 1 Sep 2021.

Builds on

62 of 123 references.

References · 62

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2020End-to-End Object Detection with Transformerscited by 7,414
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  4. 2021Transformers in Vision: A Surveycited by 1,013
  5. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
  6. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 692
  7. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 549
  8. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 480
  9. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 473
  10. 2019Omni-Scale Feature Learning for Person Re-Identificationcited by 295
  11. 2018Learning Discriminative Features with Multiple Granularities for Person Re-Identificationcited by 291
  12. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 281
38 more
  1. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 215
  2. 2019Joint Discriminative and Generative Learning for Person Re-identificationcited by 213
  3. 2020Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDcited by 212
  4. 2018Harmonious Attention Network for Person Re-Identificationcited by 211
  5. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
  6. 2017Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identificationcited by 168
  7. 2019Deeper and Wider Siamese Networks for Real-Time Visual Trackingcited by 156
  8. 2017Person Search with Natural Language Descriptioncited by 149
  9. 2019Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identificationcited by 133
  10. 2020Unsupervised Person Re-identification via Multi-label Classificationcited by 107
  11. 2020High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identificationcited by 106
  12. 2020Long-Term Cloth-Changing Person Re-identificationcited by 85
  13. 2019Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identificationcited by 83
  14. 2020AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identificationcited by 81
  15. 2020Cross-modality Person re-identification with Shared-Specific Feature Transfercited by 80
  16. 2020Unsupervised Person Re-identification via Softened Similarity Learningcited by 75
  17. 2017Unsupervised Person Re-identification: Clustering and Fine-tuningcited by 73
  18. 2020Pose-guided Visible Part Matching for Occluded Person ReIDcited by 70
  19. 2019Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identificationcited by 69
  20. 2017Deeply-Learned Part-Aligned Representations for Person Re-Identificationcited by 68
  21. 2018Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identificationcited by 62
  22. 2021Group-aware Label Transfer for Domain Adaptive Person Re-identificationcited by 58
  23. 2020Multiple Expert Brainstorming for Domain Adaptive Person Re-identificationcited by 56
  24. 2019Unsupervised Tracklet Person Re-Identificationcited by 55
  25. 2019Self-training with progressive augmentation for unsupervised cross-domain person re-identificationcited by 55
  26. 2019Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identificationcited by 53
  27. 2017Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identificationcited by 52
  28. 2021Intra-Inter Camera Similarity for Unsupervised Person Re-Identificationcited by 52
  29. 2018Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identificationcited by 50
  30. 2018Unsupervised Person Re-identification by Deep Learning Tracklet Associationcited by 45
  31. 2018Domain Adaptation through Synthesis for Unsupervised Person Re-identificationcited by 44
  32. 2019Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptationcited by 44
  33. 2020Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identificationcited by 42
  34. 2016Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identificationcited by 41
  35. 2019Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identificationcited by 37
  36. 2018Multi-task Mid-level Feature Alignment Network for Unsupervised Cross-Dataset Person Re-Identificationcited by 34
  37. 2019A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identificationcited by 32
  38. 2021Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identificationcited by 29

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1; 2024: 1; 2025: 2.

7 papers.

  1. 2022Deep Learning-based Occluded Person Re-identification: A Surveycited by 12
  2. 2022Learning to Purification for Unsupervised Person Re-identificationcited by 11
  3. 2023Deep Learning for Video-based Person Re-Identification: A Surveycited by 3
  4. 2024Test-time Similarity Modification for Person Re-identification toward Temporal Distribution Shiftcited by 3
  5. 2022Confidence-guided Centroids for Unsupervised Person Re-Identificationcited by 2
  6. 2025Contextualized Multimodal Lifelong Person Re-Identification in Hybrid Clothing Statescited by 0
  7. 2025A review of Recent Techniques for Person Re-Identificationcited by 0