# Domain Generalized Person Re-Identification via Cross-Domain Episodic Learning

arXiv: https://arxiv.org/abs/2010.09561 · HTML: https://mlsanity.com/paper/2010.09561/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2020.

## Built on by (most cited first, 7 of 7)

- [Deep Frequency Filtering for Domain Generalization](https://mlsanity.com/paper/2203.12198/) (2022)
- [Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification](https://mlsanity.com/paper/2203.01723/) (2022)
- [CLIP-DFGS: A Hard Sample Mining Method for CLIP in Generalizable Person Re-Identification](https://mlsanity.com/paper/2410.11255/) (2024)
- [Label Distribution Learning for Generalizable Multi-source Person Re-identification](https://mlsanity.com/paper/2204.05903/) (2022)
- [Generalizable Metric Network for Cross-domain Person Re-identification](https://mlsanity.com/paper/2306.11991/) (2023)
- [Calibrated Feature Decomposition for Generalizable Person Re-Identification](https://mlsanity.com/paper/2111.13945/) (2021)
- [Adaptive Domain-Specific Normalization for Generalizable Person Re-Identification](https://mlsanity.com/paper/2105.03042/) (2021)

## Abstract (arXiv)

Aiming at recognizing images of the same person across distinct camera views, person re-identification (re-ID) has been among active research topics in computer vision. Most existing re-ID works require collection of a large amount of labeled image data from the scenes of interest. When the data to be recognized are different from the source-domain training ones, a number of domain adaptation approaches have been proposed. Nevertheless, one still needs to collect labeled or unlabelled target-domain data during training. In this paper, we tackle an even more challenging and practical setting, domain generalized (DG) person re-ID. That is, while a number of labeled source-domain datasets are available, we do not have access to any target-domain training data. In order to learn domain-invariant features without knowing the target domain of interest, we present an episodic learning scheme which advances meta learning strategies to exploit the observed source-domain labeled data. The learned features would exhibit sufficient domain-invariant properties while not overfitting the source-domain data or ID labels. Our experiments on four benchmark datasets confirm the superiority of our method over the state-of-the-arts.