PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A Multiple Kernel Learning Approach to Joint Multi-Class Object Detection
Christoph Lampert and Matthew Blaschko
In: 30th Annual Symposium of the German Association for Pattern Recognition (DAGM), 10-13 Jun 2008, Munich, Germany.


Most current methods for multi-class object classification and localization work as independent 1-vs-rest classifiers. They decide whether and where an object is visible in an image purely on a per-class basis. Joint learning of more than one object class would generally be preferable, since this would allow the use of contextual information such as co-occurrence between classes. However, this approach is usually not employed because of its computational cost. In this paper we propose a method to combine the efficiency of single class localization with a subsequent decision process that works jointly for all given object classes. By following a multiple kernel learning (MKL) approach, we automatically obtain a sparse dependency graph of relevant object classes on which to base the decision. Experiments on the PASCAL VOC 2006 and 2007 datasets show that the subsequent joint decision step clearly improves the accuracy compared to single class detection.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Oral)
Additional Information:DAGM Main Prize 2008
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:4789
Deposited By:Christoph Lampert
Deposited On:24 March 2009