loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Tiago de C. G. Pereira and Teofilo E. de Campos

Affiliation: Departmento de Ciência da Computação, Universidade de Brasília - UnB, Brasília-DF, Brazil

Keyword(s): Unsupervised Domain Adaptation, Person Re-Identification, Pseudo-labels, Deep Learning.

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. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.191.202.45

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
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; ISSN 2184-4321, SciTePress, pages 484-493. DOI: 10.5220/0010843500003124

@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},
issn={2184-4321},
}

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
IS - 2184-4321
AU - Pereira, T.
AU - E. de Campos, T.
PY - 2022
SP - 484
EP - 493
DO - 10.5220/0010843500003124
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic