Age Label Distribution Learning Based on Unsupervised Comparisons of Faces

Although label distribution learning has made significant progress in the field of face age estimation, unsupervised learning has not been widely adopted and is still an important and challenging task. In this work, we propose an unsupervised contrastive label distribution learning method (UCLD) for...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Qiyuan Li, Zongyong Deng, Weichang Xu, Zhendong Li, Hao Liu
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi-Wiley 2021
Materias:	Technology T Telecommunication TK5101-6720
Acceso en línea:	https://doaj.org/article/9640fe6736fd4ff3a1698e9e7d3de9cb
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9640fe6736fd4ff3a1698e9e7d3de9cb
record_format	dspace
spelling	oai:doaj.org-article:9640fe6736fd4ff3a1698e9e7d3de9cb2021-11-22T01:10:39ZAge Label Distribution Learning Based on Unsupervised Comparisons of Faces1530-867710.1155/2021/1996803https://doaj.org/article/9640fe6736fd4ff3a1698e9e7d3de9cb2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/1996803https://doaj.org/toc/1530-8677Although label distribution learning has made significant progress in the field of face age estimation, unsupervised learning has not been widely adopted and is still an important and challenging task. In this work, we propose an unsupervised contrastive label distribution learning method (UCLD) for facial age estimation. This method is helpful to extract semantic and meaningful information of raw faces with preserving high-order correlation between adjacent ages. Similar to the processing method of wireless sensor network, we designed the ConAge network with the contrast learning method. As a result, our model maximizes the similarity of positive samples by data enhancement and simultaneously pushes the clusters of negative samples apart. Compared to state-of-the-art methods, we achieve compelling results on the widely used benchmark, i.e., MORPH.Qiyuan LiZongyong DengWeichang XuZhendong LiHao LiuHindawi-WileyarticleTechnologyTTelecommunicationTK5101-6720ENWireless Communications and Mobile Computing, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Technology T Telecommunication TK5101-6720
spellingShingle	Technology T Telecommunication TK5101-6720 Qiyuan Li Zongyong Deng Weichang Xu Zhendong Li Hao Liu Age Label Distribution Learning Based on Unsupervised Comparisons of Faces
description	Although label distribution learning has made significant progress in the field of face age estimation, unsupervised learning has not been widely adopted and is still an important and challenging task. In this work, we propose an unsupervised contrastive label distribution learning method (UCLD) for facial age estimation. This method is helpful to extract semantic and meaningful information of raw faces with preserving high-order correlation between adjacent ages. Similar to the processing method of wireless sensor network, we designed the ConAge network with the contrast learning method. As a result, our model maximizes the similarity of positive samples by data enhancement and simultaneously pushes the clusters of negative samples apart. Compared to state-of-the-art methods, we achieve compelling results on the widely used benchmark, i.e., MORPH.
format	article
author	Qiyuan Li Zongyong Deng Weichang Xu Zhendong Li Hao Liu
author_facet	Qiyuan Li Zongyong Deng Weichang Xu Zhendong Li Hao Liu
author_sort	Qiyuan Li
title	Age Label Distribution Learning Based on Unsupervised Comparisons of Faces
title_short	Age Label Distribution Learning Based on Unsupervised Comparisons of Faces
title_full	Age Label Distribution Learning Based on Unsupervised Comparisons of Faces
title_fullStr	Age Label Distribution Learning Based on Unsupervised Comparisons of Faces
title_full_unstemmed	Age Label Distribution Learning Based on Unsupervised Comparisons of Faces
title_sort	age label distribution learning based on unsupervised comparisons of faces
publisher	Hindawi-Wiley
publishDate	2021
url	https://doaj.org/article/9640fe6736fd4ff3a1698e9e7d3de9cb
work_keys_str_mv	AT qiyuanli agelabeldistributionlearningbasedonunsupervisedcomparisonsoffaces AT zongyongdeng agelabeldistributionlearningbasedonunsupervisedcomparisonsoffaces AT weichangxu agelabeldistributionlearningbasedonunsupervisedcomparisonsoffaces AT zhendongli agelabeldistributionlearningbasedonunsupervisedcomparisonsoffaces AT haoliu agelabeldistributionlearningbasedonunsupervisedcomparisonsoffaces
_version_	1718418356721156096

Age Label Distribution Learning Based on Unsupervised Comparisons of Faces

Ejemplares similares