Pairwise Identity Verification via Linear Concentrative Metric Learning

This paper presents a study of metric learning systems on pairwise identity verification, including pairwise face verification and pairwise speaker verification, respectively. These problems are challenging because the individuals in training and testing are mutually exclusive, and also due to the p...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on cybernetics 2018-01, Vol.48 (1), p.324-335
Main Authors: Lilei Zheng, Duffner, Stefan, Idrissi, Khalid, Garcia, Christophe, Baskurt, Atilla
Format: Article
Language:English
Subjects:
Computer Science
Computer Vision and Pattern Recognition
Cost function
Data models
Face
Face recognition
Face verification
identity verification
Image Processing
Learning systems
Machine Learning
Measurement
metric learning
Neural and Evolutionary Computing
pairwise metric
Robotics
siamese neural networks
speaker verification
Training
Training data
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a study of metric learning systems on pairwise identity verification, including pairwise face verification and pairwise speaker verification, respectively. These problems are challenging because the individuals in training and testing are mutually exclusive, and also due to the probable setting of limited training data. For such pairwise verification problems, we present a general framework of metric learning systems and employ the stochastic gradient descent algorithm as the optimization solution. We have studied both similarity metric learning and distance metric learning systems, of either a linear or shallow nonlinear model under both restricted and unrestricted training settings. Extensive experiments demonstrate that with limited training pairs, learning a linear system on similar pairs only is preferable due to its simplicity and superiority, i.e., it generally achieves competitive performance on both the labeled faces in the wild face dataset and the NIST speaker dataset. It is also found that a pretrained deep nonlinear model helps to improve the face verification results significantly.
ISSN:2168-2267
2168-2275
DOI:10.1109/TCYB.2016.2634011