Articles


Document Type
Journal article (JA)
Title
Multi-label learning based deep transfer neural network for facial attribute classification
Author
Zhuang, Ni(1); Yan, Yan(1); Chen, Si(2); Wang, Hanzi(1); Shen, Chunhua(3)
Address
(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
RPAddress
Email
ResearchID
ORCID
Journal
Pattern Recognition
Publisher
Elsevier Ltd
ISSN
0031-3203
Published
2018-08, 80:225-240.
JCR
2
ImpactFactor
4.582
ISBN
Fund_Code
HYMC
HYDD
HYKSRQ
HYJSRQ
HYLWLB
HYJB
Keywords
Convolution - Deep learning - Face recognition - Neural networks
Abstract
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
WOS Categories
Accession Number
EI收录号
20181404978134
DOI
10.1016/j.patcog.2018.03.018
ESI_Type
ENGINEERING
Collection
EI

Back to List