Authors:
David Masip
1
;
Àgata Lapedriza
2
and
Jordi Vitrià
2
Affiliations:
1
University of Barcelona (UB), Spain
;
2
Universitat Autònoma de Barcelona, Spain
Keyword(s):
Face verification, Computer Vision, Logistic Regression Model, Multi-task Learning.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Data Manipulation
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Methodologies and Methods
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Soft Computing
Abstract:
In face verification problems the number of training samples from each class is usually reduced, making difficult the estimation of the classifier parameters. In this paper we propose a new method for face verification where we simultaneously train different face verification tasks, sharing the model parameter space. We use a multi-task extended logistic regression classifier to perform the classification. Our approach allows to share information from different classification tasks (transfer knowledge), mitigating the effects of the reduced sample size problem. Our experiments performed using the publicly available AR Face Database, show lower error rates when multiple tasks are jointly trained sharing information, which confirms the theoretical approx- imations in the related literature.