# Federated and Generalized Person Re-identification through Domain and Feature Hallucinating

arXiv: https://arxiv.org/abs/2203.02689 · HTML: https://mlsanity.com/paper/2203.02689/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 44 references that are in the map.
- First posted on arXiv 5 Mar 2022.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://mlsanity.com/paper/1804.01438/) (2018)
- [FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space](https://mlsanity.com/paper/2103.06030/) (2021)
- [No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data](https://mlsanity.com/paper/2106.05001/) (2021)
- [Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID](https://mlsanity.com/paper/2006.02713/) (2020)
- [Style Normalization and Restitution for Generalizable Person Re-identification](https://mlsanity.com/paper/2005.11037/) (2020)
- [Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/1904.01990/) (2019)
- [Learning to Balance Specificity and Invariance for In and Out of Domain Generalization](https://mlsanity.com/paper/2008.12839/) (2020)
- [Open Domain Generalization with Domain-Augmented Meta-Learning](https://mlsanity.com/paper/2104.03620/) (2021)
- [Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification](https://mlsanity.com/paper/2012.00417/) (2020)
- [FedMix: Approximation of Mixup under Mean Augmented Federated Learning](https://mlsanity.com/paper/2107.00233/) (2021)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Unsupervised Multi-source Domain Adaptation Without Access to Source Data](https://mlsanity.com/paper/2104.01845/) (2021)

## Built on by (most cited first, 4 of 4)

- [Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges](https://mlsanity.com/paper/2207.11759/) (2022)
- [CORE-ReID: Comprehensive Optimization and Refinement through Ensemble fusion in Domain Adaptation for person re-identification](https://mlsanity.com/paper/2508.03064/) (2025)
- [CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion](https://mlsanity.com/paper/2508.04036/) (2025)
- [FedBPrompt: Federated Domain Generalization Person Re-Identification via Body Distribution Aware Visual Prompts](https://mlsanity.com/paper/2603.12912/) (2026)

## Abstract (arXiv)

In this paper, we study the problem of federated domain generalization (FedDG) for person re-identification (re-ID), which aims to learn a generalized model with multiple decentralized labeled source domains. An empirical method (FedAvg) trains local models individually and averages them to obtain the global model for further local fine-tuning or deploying in unseen target domains. One drawback of FedAvg is neglecting the data distributions of other clients during local training, making the local model overfit local data and producing a poorly-generalized global model. To solve this problem, we propose a novel method, called "Domain and Feature Hallucinating (DFH)", to produce diverse features for learning generalized local and global models. Specifically, after each model aggregation process, we share the Domain-level Feature Statistics (DFS) among different clients without violating data privacy. During local training, the DFS are used to synthesize novel domain statistics with the proposed domain hallucinating, which is achieved by re-weighting DFS with random weights. Then, we propose feature hallucinating to diversify local features by scaling and shifting them to the distribution of the obtained novel domain. The synthesized novel features retain the original pair-wise similarities, enabling us to utilize them to optimize the model in a supervised manner. Extensive experiments verify that the proposed DFH can effectively improve the generalization ability of the global model. Our method achieves the state-of-the-art performance for FedDG on four large-scale re-ID benchmarks.