Learn by Guessing: Multi-step Pseudo-label Refinement for Person Re-Identification

Tiago de C. G. Pereira, Teofilo E. de Campos

2022

Abstract

Unsupervised Domain Adaptation (UDA) methods for person Re-Identification (Re-ID) rely on target domain samples to model the marginal distribution of the data. To deal with the lack of target domain labels, UDA methods leverage information from labeled source samples and unlabeled target samples. A promising approach relies on the use of unsupervised learning as part of the pipeline, such as clustering methods. The quality of the clusters clearly plays a major role in methods performance, but this point has been overlooked. In this work, we propose a multi-step pseudo-label refinement method to select the best possible clusters and keep improving them so that these clusters become closer to the class divisions without knowledge of the class labels. Our refinement method includes a cluster selection strategy and a camera-based normalization method which reduces the within-domain variations caused by the use of multiple cameras in person Re-ID. This allows our method to reach state-of-the-art UDA results on DukeMTMC→Market1501 (source→target). We surpass state-of-the-art for UDA Re-ID by 3.4% on Market1501→DukeMTMC datasets, which is a more challenging adaptation setup because the target domain (DukeMTMC) has eight distinct cameras. Furthermore, the camera-based normalization method causes a significant reduction in the number of iterations required for training convergence.

Paper Citation

in Harvard Style

Pereira T. and E. de Campos T. (2022). Learn by Guessing: Multi-step Pseudo-label Refinement for Person Re-Identification. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 484-493. DOI: 10.5220/0010843500003124

in Bibtex Style

@conference{visapp22,
author={Tiago de C. G. Pereira and Teofilo E. de Campos},
title={Learn by Guessing: Multi-step Pseudo-label Refinement for Person Re-Identification},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={484-493},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010843500003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - Learn by Guessing: Multi-step Pseudo-label Refinement for Person Re-Identification
SN - 978-989-758-555-5
AU - Pereira T.
AU - E. de Campos T.
PY - 2022
SP - 484
EP - 493
DO - 10.5220/0010843500003124
PB - SciTePress