A Deep Face Identification Network Enhanced by Facial Attributes Prediction

被引:25
作者
Taherkhani, Fariborz [1 ]
Nasrabadi, Nasser M. [1 ]
Dawson, Jeremy [1 ]
机构
[1] West Virginia Univ, Morgantown, WV 26506 USA
来源
PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) | 2018年
关键词
D O I
10.1109/CVPRW.2018.00097
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we propose a new deep framework which predicts facial attributes and leverage it as a soft modality to improve face identification performance. Our model is an end to end framework which consists of a convolutional neural network (CNN) whose output is fanned out into two separate branches; the first branch predicts facial attributes while the second branch identifies face images. Contrary to the existing multi-task methods which only use a shared CNN feature space to train these two tasks jointly, we fuse the predicted attributes with the features from the face modality in order to improve the face identification performance. Experimental results show that our model brings benefits to both face identification as well as facial attribute prediction performance, especially in the case of identity facial attributes such as gender prediction. We tested our model on two standard datasets annotated by identities and face attributes. Experimental results indicate that the proposed model outperforms most of the current existing face identification and attribute prediction methods.
引用
收藏
页码:666 / 673
页数:8
相关论文
共 39 条
[1]   Face description with local binary patterns:: Application to face recognition [J].
Ahonen, Timo ;
Hadid, Abdenour ;
Pietikainen, Matti .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (12) :2037-2041
[2]  
[Anonymous], 2016, Asian Conference on Computer Vision
[3]  
[Anonymous], 2016, PROC CVPR IEEE, DOI [DOI 10.1109/CVPR.2016.319, 10.1109/CVPR.2016.319]
[4]   POOF: Part-Based One-vs-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation [J].
Berg, Thomas ;
Belhumeur, Peter N. .
2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, :955-962
[5]   Unconstrained Face Recognition: Identifying a Person of Interest From a Media Collection [J].
Best-Rowden, Lacey ;
Han, Hu ;
Otto, Charles ;
Klare, Brendan F. ;
Jain, Anil K. .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2014, 9 (12) :2144-2157
[6]  
Bourdev L. D., 2016, US Patent, Patent No. [9,400,925. 2, 9400925]
[7]  
Bourdev L, 2011, IEEE I CONF COMP VIS, P1543, DOI 10.1109/ICCV.2011.6126413
[8]  
Chen D, 2012, LECT NOTES COMPUT SC, V7574, P566, DOI 10.1007/978-3-642-33712-3_41
[9]  
Chung J., 2012, DEEP LEARN UNS FEAT, V3
[10]   Facial Attributes Classification using Multi-Task Representation Learning [J].
Ehrlich, Max ;
Shields, Timothy J. ;
Almaev, Timur ;
Amer, Mohamed R. .
PROCEEDINGS OF 29TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, (CVPRW 2016), 2016, :752-760