Deep Regression Neural Network for End-to-End Person Re-Identification

Person re-identification can be seen as a process of open set recognition. Usually, the deep learning models consider the person re-identification model as a classification model with a softmax layer. However, the softmax layer cannot be extended to unknown classes because of its closed nature, so t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yingchun Guo, Kunpeng Zhao, Xiaoke Hao, Ming Yu
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2019
Materias:	Person re-identification adaptive multi-label fusion deep regression neural network probabilistic regression Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/4c366b2cc29b475aa17f9eebdd9aaf58
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4c366b2cc29b475aa17f9eebdd9aaf58
record_format	dspace
spelling	oai:doaj.org-article:4c366b2cc29b475aa17f9eebdd9aaf582021-11-19T00:03:00ZDeep Regression Neural Network for End-to-End Person Re-Identification2169-353610.1109/ACCESS.2019.2927626https://doaj.org/article/4c366b2cc29b475aa17f9eebdd9aaf582019-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/8758104/https://doaj.org/toc/2169-3536Person re-identification can be seen as a process of open set recognition. Usually, the deep learning models consider the person re-identification model as a classification model with a softmax layer. However, the softmax layer cannot be extended to unknown classes because of its closed nature, so the classification model is just regarded as the feature extractor. To overcome the problem mentioned above and make the person re-identification process end-to-end, this paper cast the person re-identification into a regression process and calculates the probability that persons in the images belong to the same identity. First, this paper proposes a deep regression model, named deep regression neural network integrating adaptive multi-attribute fusion method (DRNN-AMAF), which can make the person re-identification as regression analysis. Second, attributes are taken as the basis of this model for calculating the probability of persons belonging to the same identity, and each attribute corresponds to each branch of the deep regression neural network. Finally, hard labels of multiple attributes are adaptively fused into a soft label by the proposed multi-label fusion method based on the idea of Bayesian inference, which makes the attribute labels suitable for regression tasks. The comprehensive experiments on available public databases are conducted, and the experimental results show that our model produces competitive performance compared with the state-of-the-art approaches.Yingchun GuoKunpeng ZhaoXiaoke HaoMing YuIEEEarticlePerson re-identificationadaptive multi-label fusiondeep regression neural networkprobabilistic regressionElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 7, Pp 92825-92837 (2019)
institution	DOAJ
collection	DOAJ
language	EN
topic	Person re-identification adaptive multi-label fusion deep regression neural network probabilistic regression Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Person re-identification adaptive multi-label fusion deep regression neural network probabilistic regression Electrical engineering. Electronics. Nuclear engineering TK1-9971 Yingchun Guo Kunpeng Zhao Xiaoke Hao Ming Yu Deep Regression Neural Network for End-to-End Person Re-Identification
description	Person re-identification can be seen as a process of open set recognition. Usually, the deep learning models consider the person re-identification model as a classification model with a softmax layer. However, the softmax layer cannot be extended to unknown classes because of its closed nature, so the classification model is just regarded as the feature extractor. To overcome the problem mentioned above and make the person re-identification process end-to-end, this paper cast the person re-identification into a regression process and calculates the probability that persons in the images belong to the same identity. First, this paper proposes a deep regression model, named deep regression neural network integrating adaptive multi-attribute fusion method (DRNN-AMAF), which can make the person re-identification as regression analysis. Second, attributes are taken as the basis of this model for calculating the probability of persons belonging to the same identity, and each attribute corresponds to each branch of the deep regression neural network. Finally, hard labels of multiple attributes are adaptively fused into a soft label by the proposed multi-label fusion method based on the idea of Bayesian inference, which makes the attribute labels suitable for regression tasks. The comprehensive experiments on available public databases are conducted, and the experimental results show that our model produces competitive performance compared with the state-of-the-art approaches.
format	article
author	Yingchun Guo Kunpeng Zhao Xiaoke Hao Ming Yu
author_facet	Yingchun Guo Kunpeng Zhao Xiaoke Hao Ming Yu
author_sort	Yingchun Guo
title	Deep Regression Neural Network for End-to-End Person Re-Identification
title_short	Deep Regression Neural Network for End-to-End Person Re-Identification
title_full	Deep Regression Neural Network for End-to-End Person Re-Identification
title_fullStr	Deep Regression Neural Network for End-to-End Person Re-Identification
title_full_unstemmed	Deep Regression Neural Network for End-to-End Person Re-Identification
title_sort	deep regression neural network for end-to-end person re-identification
publisher	IEEE
publishDate	2019
url	https://doaj.org/article/4c366b2cc29b475aa17f9eebdd9aaf58
work_keys_str_mv	AT yingchunguo deepregressionneuralnetworkforendtoendpersonreidentification AT kunpengzhao deepregressionneuralnetworkforendtoendpersonreidentification AT xiaokehao deepregressionneuralnetworkforendtoendpersonreidentification AT mingyu deepregressionneuralnetworkforendtoendpersonreidentification
_version_	1718420666625032192

Deep Regression Neural Network for End-to-End Person Re-Identification

Ejemplares similares