英文论文
-
文献类型
-
Journal article (JA)
-
题名
-
Multi-label learning based deep transfer neural network for facial attribute classification
-
作者
-
Zhuang, Ni(1); Yan, Yan(1); Chen, Si(2); Wang, Hanzi(1); Shen, Chunhua(3)
-
作者单位
-
(1) Fujian Key Laboratory of Sensing and Computing for Smart City, School of Information Science and Engineering, Xiamen University, Xiamen; 361005, China; (2) School of Computer and Information Engineering, Xiamen University of Technology, Xiamen; 361024, China; (3) School of Computer Science, The University of Adelaide, Adelaide; SA; 5005, Australia
-
通讯作者地址
-
-
Email
-
-
ResearchID
-
-
ORCID
-
-
期刊名称
-
Pattern Recognition
-
出版社
-
Elsevier Ltd
-
ISSN
-
0031-3203
-
出版信息
-
2018-08, 80:225-240.
-
JCR
-
2
-
影响因子
-
5.898
-
ISBN
-
-
基金
-
-
会议名称
-
-
会议地点
-
-
会议开始日期
-
-
会议结束日期
-
-
关键词
-
Convolution - Deep learning - Face recognition - Neural networks
-
摘要
-
Deep Neural Network (DNN) has recently achieved outstanding performance in a variety of computer vision tasks, including facial attribute classification. The great success of classifying facial attributes with DNN often relies on a massive amount of labelled data. However, in real-world applications, labelled data are only provided for some commonly used attributes (such as age, gender); whereas, unlabelled data are available for other attributes (such as attraction, hairline). To address the above problem, we propose a novel deep transfer neural network method based on multi-label learning for facial attribute classification, termed FMTNet, which consists of three sub-networks: the Face detection Network (FNet), the Multi-label learning Network (MNet) and the Transfer learning Network (TNet). Firstly, based on the Faster Region-based Convolutional Neural Network (Faster R-CNN), FNet is fine-tuned for face detection. Then, MNet is fine-tuned by FNet to predict multiple attributes with labelled data, where an effective loss weight scheme is developed to explicitly exploit the correlation between facial attributes based on attribute grouping. Finally, based on MNet, TNet is trained by taking advantage of unsupervised domain adaptation for unlabelled facial attribute classification. The three sub-networks are tightly coupled to perform effective facial attribute classification. A distinguishing characteristic of the proposed FMTNet method is that the three sub-networks (FNet, MNet and TNet) are constructed in a similar network structure. Extensive experimental results on challenging face datasets demonstrate the effectiveness of our proposed method compared with several state-of-the-art methods. ? 2018 Elsevier Ltd
-
一级学科
-
-
WOS入藏号
-
-
EI收录号
-
20181404978134
-
DOI
-
10.1016/j.patcog.2018.03.018
-
ESI
-
ENGINEERING
-
收录于
-
EI
-
返回