mlsanityData to 14 Oct 2026

Domain-adaptive Person Re-identification without Cross-camera Paired Samples

arXiv 2307.06533 ↗First posted 13 Jul 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Existing person re-identification (re-ID) research mainly focuses on pedestrian identity matching across cameras in adjacent areas. However, in reality, it is inevitable to face the problem of pedestrian identity matching across long-distance scenes. The cross-camera pedestrian samples collected from long-distance scenes often have no positive samples. It is extremely challenging to use cross-camera negative samples to achieve cross-region pedestrian identity matching. Therefore, a novel domain-adaptive person re-ID method that focuses on cross-camera consistent discriminative feature learning under the supervision of unpaired samples is proposed. This method mainly includes category synergy co-promotion module (CSCM) and cross-camera consistent feature learning module (CCFLM). In CSCM, a task-specific feature recombination (FRT) mechanism is proposed. This mechanism first groups features according to their contributions to specific tasks. Then an interactive promotion learning (IPL) scheme between feature groups is developed and embedded in this mechanism to enhance feature discriminability. Since the control parameters of the specific task model are reduced after division by task, the generalization ability of the model is improved. In CCFLM, instance-level feature distribution alignment and cross-camera identity consistent learning methods are constructed. Therefore, the supervised model training is achieved under the style supervision of the target domain by exchanging styles between source-domain samples and target-domain samples, and the challenges caused by the lack of cross-camera paired samples are solved by utilizing cross-camera similar samples. In experiments, three challenging datasets are used as target domains, and the effectiveness of the proposed method is demonstrated through four experimental settings.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 38 of its 72 references that are in the map. First posted on arXiv 13 Jul 2023.

Builds on

38 of 72 references.

References · 38

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  3. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  4. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 549
  5. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 480
  6. 2021TransReID: Transformer-based Object Re-Identificationcited by 435
  7. 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 430
  8. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 281
  9. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 215
  10. 2020Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDcited by 212
  11. 2018Harmonious Attention Network for Person Re-Identificationcited by 211
  12. 2017Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identificationcited by 168
26 more
  1. 2017Pose-driven Deep Convolutional Model for Person Re-identificationcited by 86
  2. 2019Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identificationcited by 83
  3. 2020Joint Disentangling and Adaptation for Cross-Domain Person Re-Identificationcited by 83
  4. 2020AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identificationcited by 81
  5. 2021ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identificationcited by 69
  6. 2017Camera Style Adaptation for Person Re-identificationcited by 68
  7. 2022Part-based Pseudo Label Refinement for Unsupervised Person Re-identificationcited by 59
  8. 2020Multiple Expert Brainstorming for Domain Adaptive Person Re-identificationcited by 56
  9. 2021IDM: An Intermediate Domain Module for Domain Adaptive Person Re-IDcited by 51
  10. 2017Deep Representation Learning with Part Loss for Person Re-Identificationcited by 44
  11. 2016Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identificationcited by 41
  12. 2019Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identificationcited by 37
  13. 2019A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identificationcited by 32
  14. 2020Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identificationcited by 25
  15. 2019Cross-Entropy Adversarial View Adaptation for Person Re-identificationcited by 12
  16. 2019Few-Shot Deep Adversarial Learning for Video-based Person Re-identificationcited by 10
  17. 2019Single Camera Training for Person Re-identificationcited by 9
  18. 2021Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenescited by 9
  19. 2022Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentificationcited by 8
  20. 2021Unsupervised Person Re-identification with Stochastic Training Strategycited by 7
  21. 2021Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-Identificationcited by 7
  22. 2019Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domaincited by 5
  23. 2020Towards Precise Intra-camera Supervised Person Re-identificationcited by 5
  24. 2021Dual-Stream Reciprocal Disentanglement Learning for Domain Adaptation Person Re-Identificationcited by 5
  25. 2018Sharp Attention Network via Adaptive Sampling for Person Re-identificationcited by 3
  26. 2019Decomposition-Based Transfer Distance Metric Learning for Image Classificationcited by 3

Built on by

Not cited yet.