# Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labeling

arXiv: https://arxiv.org/abs/2009.09445 · HTML: https://mlsanity.com/paper/2009.09445/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2020.

## Built on by (most cited first, 12 of 12)

- [Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training](https://mlsanity.com/paper/2204.11590/) (2022)
- [Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation](https://mlsanity.com/paper/2403.04381/) (2024)
- [Unsupervised and self-adaptative techniques for cross-domain person re-identification](https://mlsanity.com/paper/2103.11520/) (2021)
- [Learning Transferable Pedestrian Representation from Multimodal Information Supervision](https://mlsanity.com/paper/2304.05554/) (2023)
- [Memory Regulation and Alignment toward Generalizer RGB-Infrared Person](https://mlsanity.com/paper/2109.08843/) (2021)
- [Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters](https://mlsanity.com/paper/2110.07897/) (2021)
- [A formal approach to good practices in Pseudo-Labeling for Unsupervised Domain Adaptive Re-Identification](https://mlsanity.com/paper/2112.12887/) (2021)
- [From Indoor To Outdoor: Unsupervised Domain Adaptive Gait Recognition](https://mlsanity.com/paper/2211.11155/) (2022)
- [Self-supervised Multi-view Clustering in Computer Vision: A Survey](https://mlsanity.com/paper/2309.09473/) (2023)
- [Pseudo-label Refinement for Improving Self-Supervised Learning Systems](https://mlsanity.com/paper/2410.14242/) (2024)
- [Is Generative Modeling-based Stylization Necessary for Domain Adaptation in Regression Tasks?](https://mlsanity.com/paper/2306.01706/) (2023)
- [Dual Consistent Constraint via Disentangled Consistency and Complementarity for Multi-view Clustering](https://mlsanity.com/paper/2504.04676/) (2025)

## Abstract (arXiv)

Person Re-Identification (re-ID) aims at retrieving images of the same person taken by different cameras. A challenge for re-ID is the performance preservation when a model is used on data of interest (target data) which belong to a different domain from the training data domain (source data). Unsupervised Domain Adaptation (UDA) is an interesting research direction for this challenge as it avoids a costly annotation of the target data. Pseudo-labeling methods achieve the best results in UDA-based re-ID. Surprisingly, labeled source data are discarded after this initialization step. However, we believe that pseudo-labeling could further leverage the labeled source data in order to improve the post-initialization training steps. In order to improve robustness against erroneous pseudo-labels, we advocate the exploitation of both labeled source data and pseudo-labeled target data during all training iterations. To support our guideline, we introduce a framework which relies on a two-branch architecture optimizing classification and triplet loss based metric learning in source and target domains, respectively, in order to allow adaptability to the target domain while ensuring robustness to noisy pseudo-labels. Indeed, shared low and mid-level parameters benefit from the source classification and triplet loss signal while high-level parameters of the target branch learn domain-specific features. Our method is simple enough to be easily combined with existing pseudo-labeling UDA approaches. We show experimentally that it is efficient and improves performance when the base method has no mechanism to deal with pseudo-label noise or for hard adaptation tasks. Our approach reaches state-of-the-art performance when evaluated on commonly used datasets, Market-1501 and DukeMTMC-reID, and outperforms the state of the art when targeting the bigger and more challenging dataset MSMT.