mlsanityData to 7 Oct 2026

Source-Guided Similarity Preservation for Online Person Re-Identification

arXiv 2402.15206 ↗First posted 23 Feb 2024cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Online Unsupervised Domain Adaptation (OUDA) for person Re-Identification (Re-ID) is the task of continuously adapting a model trained on a well-annotated source domain dataset to a target domain observed as a data stream. In OUDA, person Re-ID models face two main challenges: catastrophic forgetting and domain shift. In this work, we propose a new Source-guided Similarity Preservation (S2P) framework to alleviate these two problems. Our framework is based on the extraction of a support set composed of source images that maximizes the similarity with the target data. This support set is used to identify feature similarities that must be preserved during the learning process. S2P can incorporate multiple existing UDA methods to mitigate catastrophic forgetting. Our experiments show that S2P outperforms previous state-of-the-art methods on multiple real-to-real and synthetic-to-real challenging OUDA benchmarks.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 23 Feb 2024.

Builds on

36 of 51 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2016Learning without Forgettingcited by 2,465
  5. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,059
  6. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  7. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  8. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 547
  9. 2019Similarity-Preserving Knowledge Distillationcited by 507
  10. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 479
  11. 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 429
  12. 2017Re-ranking Person Re-identification with k-reciprocal Encodingcited by 260
24 more
  1. 2015Generative Moment Matching Networkscited by 252
  2. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 214
  3. 2020Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDcited by 212
  4. 2019Compacting, Picking and Growing for Unforgetting Continual Learningcited by 207
  5. 2017Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identificationcited by 168
  6. 2019Lifelong GAN: Continual Learning for Conditional Image Generationcited by 78
  7. 2018Memory Replay GANs: learning to generate images from new categories without forgettingcited by 76
  8. 2017Unsupervised Person Re-identification: Clustering and Fine-tuningcited by 73
  9. 2018Unsupervised Domain Adaptive Re-Identification: Theory and Practicecited by 69
  10. 2021Lifelong Person Re-Identification via Adaptive Knowledge Accumulationcited by 57
  11. 2021IDM: An Intermediate Domain Module for Domain Adaptive Person Re-IDcited by 51
  12. 2020Online Continual Learning under Extreme Memory Constraintscited by 48
  13. 2021Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mappingcited by 47
  14. 2020Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identificationcited by 42
  15. 2021Incremental Learning in Semantic Segmentation from Image Labelscited by 39
  16. 2020Lifelong Object Detectioncited by 25
  17. 2021Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identificationcited by 23
  18. 2021Lifelong Teacher-Student Network Learningcited by 18
  19. 2021Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptationcited by 18
  20. 2020Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-IDcited by 15
  21. 2022Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentificationcited by 8
  22. 2022Online Unsupervised Domain Adaptation for Person Re-identificationcited by 7
  23. 2022Unsupervised Lifelong Person Re-identification via Contrastive Rehearsalcited by 5
  24. 2019CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentificationcited by 4

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2025CORE-ReID: Comprehensive Optimization and Refinement through Ensemble fusion in Domain Adaptation for person re-identificationcited by 1
  2. 2024Privacy-Preserving Adaptive Re-Identification without Image Transfercited by 0
  3. 2025CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusioncited by 0