Local Large-Margin Multi-Metric Learning for Face and Kinship Verification
- 7 April 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 28 (8) , 1875-1891
Abstract
Metric learning has attracted wide attention in face and kinship verification, and a number of such algorithms have been presented over the past few years. However, most existing metric learning methods learn only one Mahalanobis distance metric from a single feature representation for each face image and cannot make use of multiple feature representations directly. In many face-related tasks, we can easily extract multiple features for a face image to extract more complementary information, and it is desirable to learn distance metrics from these multiple features, so that more discriminative information can be exploited than those learned from individual features. To achieve this, we present a large-margin multi-metric learning (LM 3 L) method for face and kinship verification, which jointly learns multiple global distance metrics under which the correlations of different feature representations of each sample are maximized, and the distance of each positive pair is less than a low threshold and that of each negative pair is greater than a high threshold. To better exploit the local structures of face images, we also propose a local metric learning and local LM 3 Lmethods to learn a set of local metrics. Experimental results on three face data sets show that the proposed methods achieve very competitive results compared with the state-of-the-art methods.Keywords
Funding Information
- National Key Research and Development Program of China (2016YFB1001001)
- National Natural Science Foundation of China (61672306, 61572271, 61527808, 61373074, 61373090)
- National 1000 Young Talents Plan Program, the National Basic Research Program of China (2014CB349304)
- Ministry of Education of China (20120002110033)
- Tsinghua University
This publication has 49 references indexed in Scilit:
- Localized Multifeature Metric Learning for Image-Set-Based Face RecognitionIEEE Transactions on Circuits and Systems for Video Technology, 2015
- Convolutional Fusion Network for Face Verification in the WildIEEE Transactions on Circuits and Systems for Video Technology, 2015
- Semi-Local Structure Patterns for Robust Face DetectionIEEE Signal Processing Letters, 2014
- Class-Specific Kernel Fusion of Multiple Descriptors for Face Verification Using Multiscale Binarised Statistical Image FeaturesIEEE Transactions on Information Forensics and Security, 2014
- Discriminative Multimetric Learning for Kinship VerificationIEEE Transactions on Information Forensics and Security, 2014
- A Novel Local Pattern Descriptor—Local Vector Pattern in High-Order Derivative Space for Face RecognitionIEEE Transactions on Image Processing, 2014
- Local Metric Learning for Exemplar-Based Object DetectionIEEE Transactions on Circuits and Systems for Video Technology, 2014
- Neighborhood Repulsed Metric Learning for Kinship VerificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Learning Discriminant Face DescriptorIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004