PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Multi-task Learning via Non-sparse Multiple Kernel Learning
Wojciech Samek, Alexander Binder and Motoaki Kawanabe
In: Computer Analysis of Images and Patterns Lecture Notes in Computer Science , 6854 . (2011) Springer Berlin / Heidelberg , pp. 335-342. ISBN 978-3-642-23671-6


In object classification tasks from digital photographs, multiple categories are considered for annotation. Some of these visual concepts may have semantic relations and can appear simultaneously in images. Although taxonomical relations and co-occurrence structures between object categories have been studied, it is not easy to use such information to enhance performance of object classification. In this paper, we propose a novel multi-task learning procedure which extracts useful information from the classifiers for the other categories. Our approach is based on non-sparse multiple kernel learning (MKL) which has been successfully applied to adaptive feature selection for image classification. Experimental results on PASCAL VOC 2009 data show the potential of our method.

EPrint Type:Book Section
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:9438
Deposited By:Wojciech Samek
Deposited On:16 March 2012