PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

On taxonomies for multi-class image categorization
Alexander Binder, Klaus-Robert Müller and Motoaki Kawanabe
International Journal of Computer Vision pp. 1-21, 2011.

Abstract

We study the problem of classifying images into a given, pre-determined taxonomy. This task can be elegantly translated into the structured learning framework. However, despite its power, structured learning has known limits in scalability due to its high memory requirements and slow training process. We propose an efficient approximation of the structured learning approach by an ensemble of local support vector machines ({SVMs}) that can be trained efficiently with standard techniques. A first theoretical discussion and experiments on toy-data allow to shed light onto why taxonomy-based classification can outperform taxonomy-free approaches and why an appropriately combined ensemble of local {SVMs} might be of high practical use. Further empirical results on subsets of Caltech256 and {VOC2006} data indeed show that our local {SVM} formulation can effectively exploit the taxonomy structure and thus outperforms standard multi-class classification algorithms while it achieves on par results with taxonomy-based structured algorithms at a significantly decreased computing time.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
Information Retrieval & Textual Information Access
ID Code:8006
Deposited By:Alexander Binder
Deposited On:17 March 2011