# Multi-Domain Adversarial Feature Generalization for Person Re-Identification

arXiv: https://arxiv.org/abs/2011.12563 · HTML: https://mlsanity.com/paper/2011.12563/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2020.

## Built on by (most cited first, 22 of 22)

- [Learning Domain Invariant Representations for Generalizable Person Re-Identification](https://mlsanity.com/paper/2103.15890/) (2021)
- [MADG: Margin-based Adversarial Learning for Domain Generalization](https://mlsanity.com/paper/2311.08503/) (2023)
- [TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenes](https://mlsanity.com/paper/2308.11157/) (2023)
- [Domain-Specific Bias Filtering for Single Labeled Domain Generalization](https://mlsanity.com/paper/2110.00726/) (2021)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification](https://mlsanity.com/paper/2203.01723/) (2022)
- [Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification](https://mlsanity.com/paper/2105.12355/) (2021)
- [DEX: Domain Embedding Expansion for Generalized Person Re-identification](https://mlsanity.com/paper/2110.11391/) (2021)
- [Towards Generalizable Person Re-identification with a Bi-stream Generative Model](https://mlsanity.com/paper/2206.09362/) (2022)
- [Rethinking Sampling Strategies for Unsupervised Person Re-identification](https://mlsanity.com/paper/2107.03024/) (2021)
- [INSURE: An Information Theory Inspired Disentanglement and Purification Model for Domain Generalization](https://mlsanity.com/paper/2309.04063/) (2023)
- [Exploring Flat Minima for Domain Generalization with Large Learning Rates](https://mlsanity.com/paper/2309.06337/) (2023)
- [A Unified Deep Semantic Expansion Framework for Domain-Generalized Person Re-identification](https://mlsanity.com/paper/2410.08456/) (2024)
- [TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2111.14290/) (2021)
- [Style Variable and Irrelevant Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2209.05235/) (2022)
- [Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2408.02039/) (2024)
- [Adaptive Domain-Specific Normalization for Generalizable Person Re-Identification](https://mlsanity.com/paper/2105.03042/) (2021)
- [Generalizable Person Search on Open-world User-Generated Video Content](https://mlsanity.com/paper/2310.10068/) (2023)
- [Diverse Deep Feature Ensemble Learning for Omni-Domain Generalized Person Re-identification](https://mlsanity.com/paper/2410.08460/) (2024)
- [Aligned Divergent Pathways for Omni-Domain Generalized Person Re-Identification](https://mlsanity.com/paper/2410.08466/) (2024)
- [Source-Free Domain Adaptation via Multi-view Contrastive Learning](https://mlsanity.com/paper/2507.03321/) (2025)
- [Coordinated Disentanglement with Iterative Mode Discovery Under Hidden Correlations](https://mlsanity.com/paper/2607.17264/) (2026)

## Abstract (arXiv)

With the assistance of sophisticated training methods applied to single labeled datasets, the performance of fully-supervised person re-identification (Person Re-ID) has been improved significantly in recent years. However, these models trained on a single dataset usually suffer from considerable performance degradation when applied to videos of a different camera network. To make Person Re-ID systems more practical and scalable, several cross-dataset domain adaptation methods have been proposed, which achieve high performance without the labeled data from the target domain. However, these approaches still require the unlabeled data of the target domain during the training process, making them impractical. A practical Person Re-ID system pre-trained on other datasets should start running immediately after deployment on a new site without having to wait until sufficient images or videos are collected and the pre-trained model is tuned. To serve this purpose, in this paper, we reformulate person re-identification as a multi-dataset domain generalization problem. We propose a multi-dataset feature generalization network (MMFA-AAE), which is capable of learning a universal domain-invariant feature representation from multiple labeled datasets and generalizing it to `unseen' camera systems. The network is based on an adversarial auto-encoder to learn a generalized domain-invariant latent feature representation with the Maximum Mean Discrepancy (MMD) measure to align the distributions across multiple domains. Extensive experiments demonstrate the effectiveness of the proposed method. Our MMFA-AAE approach not only outperforms most of the domain generalization Person Re-ID methods, but also surpasses many state-of-the-art supervised methods and unsupervised domain adaptation methods by a large margin.