Transferring learning from multi-person tracking to person re-identification

e-Archivo Repository

Show simple item record Gómez Silva, María José Izquierdo, Ebroul Escalera Hueso, Arturo de la Armingol Moreno, José María 2021-01-25T13:07:06Z 2021-01-25T13:07:06Z 2019-09-11
dc.identifier.bibliographicCitation M.J. Gómez-Silva, E. Izquierdo, Escalera, A. de la and Armingol, J.M. “Transferring Learning from Multi-person Tracking to Person Re-identification”, Integrated Computer-Aided Engineering, vol. 26, nº 4, pp. 329-344, 1 Jan. 2019
dc.identifier.issn 1069-2509
dc.description.abstract Learning to discriminate, whether two person-images correspond to the same person or not, is a daunting challenge when only two images per person are available. This task is called single-shot person re-identification (re-id) and it assumes that each one of the two available images was captured from a different camera view entailing variations in pose, resolution, scale, illumination and background. Addressing this task through supervised training of a deep convolutional neural network is susceptible to model overfitting due to the critical lack of enough labelled data. This paper proposes to exploit the transference of learning previously acquired from a multi-object-tracking (MOT) domain. In this context, a unique deep triplet architecture has been trained on both domains. Six different levels of transfer learning have been implemented and evaluated, proving that the transference of leaning from a different domain remarkably increases the re-id performance. Experimental results validate accuracy and robustness of the proposed method as comparable to other state-of-the-art techniques. These results also confirm that, despite the data problem, deep learning is also applicable to the single-shot re-id task.
dc.description.sponsorship This work was supported by the Spanish Govern-ment through the CICYT projects (TRA2015-63708-R and TRA2016-78886-C3-1-R), and Ministerio de Educación, Cultura y Deporte para la Formación de Profesorado Universitario (FPU14/02143), Ayudas a la movilidad para estancias breves y traslados tempo-rales (2018) of Programa Estatal de promoción del ta-lento y su empleabilidad, , and Comunidad de Madrid through SEGVAUTO-TRIES (S2013/MIT- 2713). We gratefully acknowledge the support of NVIDIA Corporation with the donation of the GPUs used for this research.
dc.language.iso eng
dc.publisher IOP Press
dc.rights © IOS Press
dc.subject.other Transfer learning
dc.subject.other Deep learning
dc.subject.other Person re-identification
dc.subject.other Multi-object tracking
dc.subject.other Pair-wise binary classification
dc.title Transferring learning from multi-person tracking to person re-identification
dc.type article
dc.subject.eciencia Robótica e Informática Industrial
dc.rights.accessRights openAccess
dc.relation.projectID Gobierno de España. TRA2015-63708-R
dc.relation.projectID Gobierno de España. TRA2016-78886-C3-1-R
dc.relation.projectID Comunidad de Madrid. S2013/MIT- 2713
dc.type.version acceptedVersion
dc.identifier.publicationfirstpage 329
dc.identifier.publicationissue 4
dc.identifier.publicationlastpage 344
dc.identifier.publicationtitle Integrated Computer-Aided Engineering
dc.identifier.publicationvolume 26
dc.identifier.uxxi AR/0000025756
dc.contributor.funder Ministerio de Economía y Competitividad (España)
dc.contributor.funder Comunidad de Madrid
dc.affiliation.dpto UC3M. Departamento de Ingeniería de Sistemas y Automática
dc.affiliation.grupoinv UC3M. Grupo de Investigación: Laboratorio de Sistemas Inteligentes
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)

This item appears in the following Collection(s)

Show simple item record