Deep Part Features Learning by a Normalised Double-Margin-Based Contrastive Loss Function for Person Re-Identification

María José Gómez-Silva, José María Armingol, Arturo de la Escalera

2017

Abstract

The selection of discriminative features that properly define a person appearance is one of the current challenges for person re-identification. This paper presents a three-dimensional representation to compare person images, which is based on the similarity, independently measured for the head, upper body, and legs from two images. Three deep Siamese neural networks have been implemented to automatically find salient features for each body part. One of the main problems in the learning of features for re-identification is the presence of intra-class variations and inter-class ambiguities. This paper proposes a novel normalized double-margin-based contrastive loss function for the training of Siamese networks, which not only improves the robustness of the learned features against the mentioned problems but also reduce the training time. A comparative evaluation over the challenging PRID 2011 dataset has been conducted, resulting in a remarkable enhancement of the single-shot re-identification performance thanks to the use of our descriptor based on deeply learned features in comparison with the employment of low-level features. The obtained results also show the improvements generated by our normalized double-margin-based function with respect to the traditional contrastive loss function.

Paper Citation

in Harvard Style

Gómez-Silva M., Armingol J. and de la Escalera A. (2017). Deep Part Features Learning by a Normalised Double-Margin-Based Contrastive Loss Function for Person Re-Identification . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-227-1, pages 277-285. DOI: 10.5220/0006167002770285

in Bibtex Style

@conference{visapp17,
author={María José Gómez-Silva and José María Armingol and Arturo de la Escalera},
title={Deep Part Features Learning by a Normalised Double-Margin-Based Contrastive Loss Function for Person Re-Identification},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={277-285},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006167002770285},
isbn={978-989-758-227-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)
TI - Deep Part Features Learning by a Normalised Double-Margin-Based Contrastive Loss Function for Person Re-Identification
SN - 978-989-758-227-1
AU - Gómez-Silva M.
AU - Armingol J.
AU - de la Escalera A.
PY - 2017
SP - 277
EP - 285
DO - 10.5220/0006167002770285