Gated Classifiers: Boosting under high intra-class variation
2011 (English)In: Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, 2011, 2673-2680 p.Conference paper (Refereed)
In this paper we address the problem of using boosting (e.g. AdaBoost ) to classify a target class with significant intra-class variation against a large background class. This situation occurs for example when we want to recognize a visual object class against all other image patches. The boosting algorithm produces a strong classifier, which is a linear combination of weak classifiers. We observe that we often have sets of weak classifiers that individually fire on many examples of the target class but never fire together on those examples (i.e. their outputs are anti-correlated on the target class). Motivated by this observation we suggest a family of derived weak classifiers, termed gated classifiers, that suppress such combinations of weak classifiers. Gated classifiers can be used on top of any original weak learner. We run experiments on two popular datasets, showing that our method reduces the required number of weak classifiers by almost an order of magnitude, which in turn yields faster detectors. We experiment on synthetic data showing that gated classifiers enables more complex distributions to be represented. We hope that gated classifiers will extend the usefulness of boosted classifier cascades .
Place, publisher, year, edition, pages
2011. 2673-2680 p.
, IEEE Conference on Computer Vision and Pattern Recognition, ISSN 1063-6919
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-38595DOI: 10.1109/CVPR.2011.5995408ISI: 000295615802108ScopusID: 2-s2.0-80052879417ISBN: 978-1-4577-0393-5OAI: oai:DiVA.org:kth-38595DiVA: diva2:437455
The 24th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011, Colorado Springs, CO, USA, 20-25 June 2011 2011
FunderICT - The Next Generation
QC 201108302011-08-292011-08-292012-01-20Bibliographically approved