mlsanityData to 7 Oct 2026

Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains

arXiv 2203.01682 ↗First posted 3 Mar 2022cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Cross-domain person re-identification (re-ID), such as unsupervised domain adaptive (UDA) re-ID, aims to transfer the identity-discriminative knowledge from the source to the target domain. Existing methods commonly consider the source and target domains are isolated from each other, i.e., no intermediate status is modeled between both domains. Directly transferring the knowledge between two isolated domains can be very difficult, especially when the domain gap is large. From a novel perspective, we assume these two domains are not completely isolated, but can be connected through intermediate domains. Instead of directly aligning the source and target domains against each other, we propose to align the source and target domains against their intermediate domains for a smooth knowledge transfer. To discover and utilize these intermediate domains, we propose an Intermediate Domain Module (IDM) and a Mirrors Generation Module (MGM). IDM has two functions: 1) it generates multiple intermediate domains by mixing the hidden-layer features from source and target domains and 2) it dynamically reduces the domain gap between the source / target domain features and the intermediate domain features. While IDM achieves good domain alignment, it introduces a side effect, i.e., the mix-up operation may mix the identities into a new identity and lose the original identities. To compensate this, MGM is introduced by mapping the features into the IDM-generated intermediate domains without changing their original identity. It allows to focus on minimizing domain variations to promote the alignment between the source / target domain and intermediate domains, which reinforces IDM into IDM++. We extensively evaluate our method under both the UDA and domain generalization (DG) scenarios and observe that IDM++ yields consistent performance improvement for cross-domain re-ID, achieving new state of the art.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 80 of its 120 references that are in the map. First posted on arXiv 3 Mar 2022.

Builds on

80 of 120 references.

References · 80

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  5. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  7. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  8. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  9. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  10. 2017Random Erasing Data Augmentationcited by 1,235
  11. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  12. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
38 more
  1. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 685
  2. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  3. 2021Domain Generalization with MixStylecited by 563
  4. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 547
  5. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 479
  6. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  7. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  8. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
  9. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  10. 2020Learning to Learn Single Domain Generalizationcited by 295
  11. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 285
  12. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 280
  13. 2017Re-ranking Person Re-identification with k-reciprocal Encodingcited by 260
  14. 2019Adversarial Domain Adaptation with Domain Mixupcited by 250
  15. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  16. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 214
  17. 2020Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDcited by 212
  18. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
  19. 2016Person Re-identification: Past, Present and Futurecited by 180
  20. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 176
  21. 2017Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identificationcited by 168
  22. 2019A Strong Baseline and Batch Normalization Neck for Deep Person Re-identificationcited by 154
  23. 2020Robust and Generalizable Visual Representation Learning via Random Convolutionscited by 141
  24. 2020Style Normalization and Restitution for Generalizable Person Re-identificationcited by 136
  25. 2019Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identificationcited by 133
  26. 2019Cross-Batch Memory for Embedding Learningcited by 130
  27. 2020Gradually Vanishing Bridge for Adversarial Domain Adaptationcited by 130
  28. 2020FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptationcited by 124
  29. 2020Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identificationcited by 110
  30. 2020Unsupervised Person Re-identification via Multi-label Classificationcited by 107
  31. 2020PointMixup: Augmentation for Point Cloudscited by 104
  32. 2020Dual Mixup Regularized Learning for Adversarial Domain Adaptationcited by 99
  33. 2018Dissecting Person Re-identification from the Viewpoint of Viewpointcited by 83
  34. 2020Joint Disentangling and Adaptation for Cross-Domain Person Re-Identificationcited by 83
  35. 2020AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identificationcited by 81
  36. 2020Meta Batch-Instance Normalization for Generalizable Person Re-Identificationcited by 77
  37. 2021Generalizable Person Re-identification with Relevance-aware Mixture of Expertscited by 77
  38. 2020Unsupervised Person Re-identification via Softened Similarity Learningcited by 75

50 most cited of 80 All 80 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 0; 2026: 1.

2 papers.

  1. 2022Learning to Purification for Unsupervised Person Re-identificationcited by 11
  2. 2026AIDA-ReID: Adaptive Intermediate Domain Adaptation for Generalizable and Source-Free Person Re-Identificationcited by 0