# Semi-Supervised Domain Generalizable Person Re-Identification

arXiv: https://arxiv.org/abs/2108.05045 · HTML: https://mlsanity.com/paper/2108.05045/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 58 references that are in the map.
- First posted on arXiv 11 Aug 2021.

## Builds on (most cited first, 30 of 38)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Variational Information Distillation for Knowledge Transfer](https://mlsanity.com/paper/1904.05835/) (2019)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Paraphrasing Complex Network: Network Compression via Factor Transfer](https://mlsanity.com/paper/1802.04977/) (2018)
- [Episodic Training for Domain Generalization](https://mlsanity.com/paper/1902.00113/) (2019)
- [Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons](https://mlsanity.com/paper/1811.03233/) (2018)
- [Joint Detection and Identification Feature Learning for Person Search](https://mlsanity.com/paper/1604.01850/) (2016)
- [Domain Generalization Using a Mixture of Multiple Latent Domains](https://mlsanity.com/paper/1911.07661/) (2019)
- [FastReID: A Pytorch Toolbox for General Instance Re-identification](https://mlsanity.com/paper/2006.02631/) (2020)
- [Style Normalization and Restitution for Generalizable Person Re-identification](https://mlsanity.com/paper/2005.11037/) (2020)
- [Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification](https://mlsanity.com/paper/2012.00417/) (2020)
- [Dissecting Person Re-identification from the Viewpoint of Viewpoint](https://mlsanity.com/paper/1812.02162/) (2018)
- [Meta Batch-Instance Normalization for Generalizable Person Re-Identification](https://mlsanity.com/paper/2011.14670/) (2020)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Occluded Person Re-identification](https://mlsanity.com/paper/1804.02792/) (2018)
- [Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach](https://mlsanity.com/paper/1801.00881/) (2018)

## Built on by (most cited first, 8 of 8)

- [Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification](https://mlsanity.com/paper/2112.08684/) (2021)
- [CLIP-DFGS: A Hard Sample Mining Method for CLIP in Generalizable Person Re-Identification](https://mlsanity.com/paper/2410.11255/) (2024)
- [CILP-FGDI: Exploiting Vision-Language Model for Generalizable Person Re-Identification](https://mlsanity.com/paper/2501.16065/) (2025)
- [Meta Clustering Learning for Large-scale Unsupervised Person Re-identification](https://mlsanity.com/paper/2111.10032/) (2021)
- [Calibrated Feature Decomposition for Generalizable Person Re-Identification](https://mlsanity.com/paper/2111.13945/) (2021)
- [Enhancing Semi-supervised Learning with Zero-shot Pseudolabels](https://mlsanity.com/paper/2502.12584/) (2025)
- [Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization](https://mlsanity.com/paper/2505.07675/) (2025)
- [PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Models](https://mlsanity.com/paper/2506.00910/) (2025)

## Abstract (arXiv)

Existing person re-identification (re-id) methods are stuck when deployed to a new unseen scenario despite the success in cross-camera person matching. Recent efforts have been substantially devoted to domain adaptive person re-id where extensive unlabeled data in the new scenario are utilized in a transductive learning manner. However, for each scenario, it is required to first collect enough data and then train such a domain adaptive re-id model, thus restricting their practical application. Instead, we aim to explore multiple labeled datasets to learn generalized domain-invariant representations for person re-id, which is expected universally effective for each new-coming re-id scenario. To pursue practicability in real-world systems, we collect all the person re-id datasets (20 datasets) in this field and select the three most frequently used datasets (i.e., Market1501, DukeMTMC, and MSMT17) as unseen target domains. In addition, we develop DataHunter that collects over 300K+ weak annotated images named YouTube-Human from YouTube street-view videos, which joins 17 remaining full labeled datasets to form multiple source domains. On such a large and challenging benchmark called FastHuman (~440K+ labeled images), we further propose a simple yet effective Semi-Supervised Knowledge Distillation (SSKD) framework. SSKD effectively exploits the weakly annotated data by assigning soft pseudo labels to YouTube-Human to improve models' generalization ability. Experiments on several protocols verify the effectiveness of the proposed SSKD framework on domain generalizable person re-id, which is even comparable to supervised learning on the target domains. Lastly, but most importantly, we hope the proposed benchmark FastHuman could bring the next development of domain generalizable person re-id algorithms.