# Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification

arXiv: https://arxiv.org/abs/2012.00417 · HTML: https://mlsanity.com/paper/2012.00417/

## Key facts

- Cited by 110 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2020.

## Built on by (most cited first, 30 of 110)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation](https://mlsanity.com/paper/2207.04892/) (2022)
- [Pin the Memory: Learning to Generalize Semantic Segmentation](https://mlsanity.com/paper/2204.03609/) (2022)
- [Simple Cues Lead to a Strong Multi-Object Tracker](https://mlsanity.com/paper/2206.04656/) (2022)
- [Deep Frequency Filtering for Domain Generalization](https://mlsanity.com/paper/2203.12198/) (2022)
- [Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification](https://mlsanity.com/paper/2104.01546/) (2021)
- [Multiple-environment Self-adaptive Network for Aerial-view Geo-localization](https://mlsanity.com/paper/2204.08381/) (2022)
- [Anomaly Detection under Distribution Shift](https://mlsanity.com/paper/2303.13845/) (2023)
- [Part-Aware Transformer for Generalizable Person Re-identification](https://mlsanity.com/paper/2308.03322/) (2023)
- [Feature-based Style Randomization for Domain Generalization](https://mlsanity.com/paper/2106.03171/) (2021)
- [Generative Domain Adaptation for Face Anti-Spoofing](https://mlsanity.com/paper/2207.10015/) (2022)
- [BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning](https://mlsanity.com/paper/2203.01522/) (2022)
- [Attention Diversification for Domain Generalization](https://mlsanity.com/paper/2210.04206/) (2022)
- [Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection](https://mlsanity.com/paper/2405.15225/) (2024)
- [Domain Generalization through Meta-Learning: A Survey](https://mlsanity.com/paper/2404.02785/) (2024)
- [Federated Domain Generalization: A Survey](https://mlsanity.com/paper/2306.01334/) (2023)
- [Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization](https://mlsanity.com/paper/2212.09068/) (2022)
- [MADG: Margin-based Adversarial Learning for Domain Generalization](https://mlsanity.com/paper/2311.08503/) (2023)
- [Transformer for Object Re-Identification: A Survey](https://mlsanity.com/paper/2401.06960/) (2024)
- [StableFDG: Style and Attention Based Learning for Federated Domain Generalization](https://mlsanity.com/paper/2311.00227/) (2023)
- [DGMamba: Domain Generalization via Generalized State Space Model](https://mlsanity.com/paper/2404.07794/) (2024)
- [Domain-General Crowd Counting in Unseen Scenarios](https://mlsanity.com/paper/2212.02573/) (2022)
- [Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification](https://mlsanity.com/paper/2112.08684/) (2021)
- [Feature Representation Learning for Unsupervised Cross-domain Image Retrieval](https://mlsanity.com/paper/2207.09721/) (2022)
- [Intra-Source Style Augmentation for Improved Domain Generalization](https://mlsanity.com/paper/2210.10175/) (2022)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges](https://mlsanity.com/paper/2309.07438/) (2023)
- [Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2308.08887/) (2023)

## Abstract (arXiv)

Recent advances in person re-identification (ReID) obtain impressive accuracy in the supervised and unsupervised learning settings. However, most of the existing methods need to train a new model for a new domain by accessing data. Due to public privacy, the new domain data are not always accessible, leading to a limited applicability of these methods. In this paper, we study the problem of multi-source domain generalization in ReID, which aims to learn a model that can perform well on unseen domains with only several labeled source domains. To address this problem, we propose the Memory-based Multi-Source Meta-Learning (M3L) framework to train a generalizable model for unseen domains. Specifically, a meta-learning strategy is introduced to simulate the train-test process of domain generalization for learning more generalizable models. To overcome the unstable meta-optimization caused by the parametric classifier, we propose a memory-based identification loss that is non-parametric and harmonizes with meta-learning. We also present a meta batch normalization layer (MetaBN) to diversify meta-test features, further establishing the advantage of meta-learning. Experiments demonstrate that our M3L can effectively enhance the generalization ability of the model for unseen domains and can outperform the state-of-the-art methods on four large-scale ReID datasets.