Deep triplet-group network by exploiting symmetric and asymmetric information for person reidentification

Benzhi Yu; Ning Xu

doi:10.1117/1.JEI.27.3.033033

9 June 2018 Deep triplet-group network by exploiting symmetric and asymmetric information for person reidentification

Benzhi Yu, Ning Xu

Author Affiliations +

Journal of Electronic Imaging, Vol. 27, Issue 3, 033033 (June 2018). https://doi.org/10.1117/1.JEI.27.3.033033

Abstract

Deep metric learning is an effective method for person reidentification. In practice, impostor samples generally possess more discriminative information than other negative samples. Specifically, existing triplet-based deep-learning methods cannot effectively remove impostors, because they cannot consider congeners of impostor and it may produce new impostors when removing existing impostors. To utilize discriminative information in triplets and make impostor and its congeners more clustering, we design oversymmetric and overasymmetric relationships and apply these two constraints to triplet and impostors’ congeners to train our deep triplet-group network with original individual images rather than handcrafted features. Extensive experiments with five benchmark datasets demonstrate that our method outperforms the state-of-the-art methods with regards to the rank-N matching accuracy.

CC BY: © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

Citation Download Citation

Benzhi Yu and Ning Xu "Deep triplet-group network by exploiting symmetric and asymmetric information for person reidentification," Journal of Electronic Imaging 27(3), 033033 (9 June 2018). https://doi.org/10.1117/1.JEI.27.3.033033

Received: 2 January 2018; Accepted: 11 May 2018; Published: 9 June 2018

ACCESS THE FULL ARTICLE

JOURNAL ARTICLE
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY