mlsanityData to 14 Oct 2026

Learning Domain Invariant Representations for Generalizable Person Re-Identification

arXiv 2103.15890 ↗First posted 29 Mar 2021cs.CV cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Generalizable person Re-Identification (ReID) has attracted growing attention in recent computer vision community. In this work, we construct a structural causal model among identity labels, identity-specific factors (clothes/shoes color etc), and domain-specific factors (background, viewpoints etc). According to the causal analysis, we propose a novel Domain Invariant Representation Learning for generalizable person Re-Identification (DIR-ReID) framework. Specifically, we first propose to disentangle the identity-specific and domain-specific feature spaces, based on which we propose an effective algorithmic implementation for backdoor adjustment, essentially serving as a causal intervention towards the SCM. Extensive experiments have been conducted, showing that DIR-ReID outperforms state-of-the-art methods on large-scale domain generalization ReID benchmarks.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 67 of its 106 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

67 of 106 references.

References · 67

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  3. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  4. 2019Invariant Risk Minimizationcited by 1,854
  5. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  6. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  7. 2020In Search of Lost Domain Generalizationcited by 1,054
  8. 2019When Does Label Smoothing Help?cited by 988
  9. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 549
  10. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
  11. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 473
  12. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 364
38 more
  1. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  2. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 281
  3. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  4. 2020The Risks of Invariant Risk Minimizationcited by 262
  5. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  6. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  7. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  8. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 215
  9. 2019Joint Discriminative and Generative Learning for Person Re-identificationcited by 213
  10. 2021Towards Causal Representation Learningcited by 209
  11. 2020Representation Learning via Invariant Causal Mechanismscited by 199
  12. 2019Domain-Specific Batch Normalization for Unsupervised Domain Adaptationcited by 197
  13. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
  14. 2020Invariant Risk Minimization Gamescited by 188
  15. 2017Beyond triplet loss: a deep quadruplet network for person re-identificationcited by 172
  16. 2017Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identificationcited by 168
  17. 2020Style Normalization and Restitution for Generalizable Person Re-identificationcited by 136
  18. 2017Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributionscited by 126
  19. 2019Relation-Aware Global Attention for Person Re-identificationcited by 124
  20. 2020Interventional Few-Shot Learningcited by 112
  21. 2020Visual Commonsense R-CNNcited by 106
  22. 2017Learning Independent Causal Mechanismscited by 105
  23. 2020A causal view of compositional zero-shot recognitioncited by 78
  24. 2019Two Causal Principles for Improving Visual Dialogcited by 75
  25. 2019Learning Generalisable Omni-Scale Representations for Person Re-Identificationcited by 74
  26. 2017Unsupervised Person Re-identification: Clustering and Fine-tuningcited by 73
  27. 2020Deconfounded Image Captioning: A Causal Retrospectcited by 65
  28. 2018Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identificationcited by 62
  29. 2020Learning Causal Semantic Representation for Out-of-Distribution Predictioncited by 60
  30. 2018Densely Semantically Aligned Person Re-Identificationcited by 58
  31. 2020Multiple Expert Brainstorming for Domain Adaptive Person Re-identificationcited by 56
  32. 2020Learning Disentangled Semantic Representation for Domain Adaptationcited by 55
  33. 2017Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identificationcited by 52
  34. 2018Counterfactuals uncover the modular structure of deep generative modelscited by 51
  35. 2019Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practicecited by 48
  36. 2018Domain Adaptation through Synthesis for Unsupervised Person Re-identificationcited by 44
  37. 2016End-to-End Comparative Attention Networks for Person Re-identificationcited by 42
  38. 2020Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identificationcited by 42

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 5; 2024: 3; 2025: 4; 2026: 2.

22 papers.

Sort:

By area:

  1. 2023OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensemblingcited by 74
  2. 2023AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptationcited by 48
  3. 2022Deep Frequency Filtering for Domain Generalizationcited by 43
  4. 2023Free Lunch for Domain Adversarial Training: Environment Label Smoothingcited by 33
  5. 2022Domain-Specific Risk Minimization for Out-of-Distribution Generalizationcited by 15
  6. 2022Domain Generalization -- A Causal Perspectivecited by 14
  7. 2023Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identificationcited by 13
  8. 2022Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identificationcited by 10
  9. 2021DEX: Domain Embedding Expansion for Generalized Person Re-identificationcited by 8
  10. 2024Generalizable Person Re-identification via Balancing Alignment and Uniformitycited by 8
  11. 2025Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identificationcited by 7
  12. 2023Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-IDcited by 6
10 more
  1. 2024A Unified Deep Semantic Expansion Framework for Domain-Generalized Person Re-identificationcited by 3
  2. 2022Feature-Distribution Perturbation and Calibration for Generalized Person ReIDcited by 2
  3. 2021Calibrated Feature Decomposition for Generalizable Person Re-Identificationcited by 1
  4. 2021Adaptive Domain-Specific Normalization for Generalizable Person Re-Identificationcited by 0
  5. 2024Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identificationcited by 0
  6. 2025Causality and "In-the-Wild" Video-Based Person Re-ID: A Surveycited by 0
  7. 2025PCD-ReID: Occluded Person Re-Identification for Base Station Inspectioncited by 0
  8. 2025Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identificationcited by 0
  9. 2026FedBPrompt: Federated Domain Generalization Person Re-Identification via Body Distribution Aware Visual Promptscited by 0
  10. 2026Multi-Grained Vision-Language Alignment for Domain Generalized Person Re-Identificationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Generalizable Person Re-identification with Relevance-aware Mixture of Experts
  2. 2023Part-Aware Transformer for Generalizable Person Re-identification
  3. 2021TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification
  4. 2026Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-Identification
  5. 2021Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification
  6. 2021Semi-Supervised Domain Generalizable Person Re-Identification
  7. 2022Learning Feature Fusion for Unsupervised Domain Adaptive Person Re-identification
  8. 2025Attribute Guidance With Inherent Pseudo-label For Occluded Person Re-identification