Show simple item record  

dc.contributor.authorMayo, Michael
dc.contributor.authorFrank, Eibe
dc.coverage.spatialConference held at Auckland, NZen_NZ
dc.date.accessioned2012-02-22T02:09:13Z
dc.date.available2012-02-22T02:09:13Z
dc.date.issued2011
dc.identifier.citationMayo, M. & Frank, E. (2011). Experiments with multi-view multi-instance learning for supervised image classification. In Proceedings 26th International Conference Image and Vision Computing New Zealand, November 29-December 1 2011, Auckland, New Zealand, pp. 363-369.en_NZ
dc.identifier.urihttps://hdl.handle.net/10289/6047
dc.description.abstractIn this paper we empirically investigate the benefits of multi-view multi-instance (MVMI) learning for supervised image classification. In multi-instance learning, examples for learning contain bags of feature vectors and thus data from different views cannot simply be concatenated as in the single-instance case. Hence, multi-view learning, where one classifier is built per view, is particularly attractive when applying multi-instance learning to image classification. We take several diverse image data sets—ranging from person detection to astronomical object classification to species recognition—and derive a set of multiple instance views from each of them. We then show via an extensive set of 10_10 stratified cross-validation experiments that MVMI, based on averaging predicted confidence scores, generally exceeds the performance of traditional single-view multi-instance learning, when using support vector machines and boosting as the underlying learning algorithms.en_NZ
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisher-en_NZ
dc.relation.urihttp://www.icivc.org/en_NZ
dc.rights© 2011 The Authorsen_NZ
dc.subjectcomputer scienceen_NZ
dc.subjectmulti-view multi-instance (MVMI) learningen_NZ
dc.subjectimage classificationen_NZ
dc.titleExperiments with multi-view multi-instance learning for supervised image classificationen_NZ
dc.typeConference Contributionen_NZ
dc.relation.isPartOfProceedings of Image and Vision Computing New Zealanden_NZ
pubs.begin-page363en_NZ
pubs.elements-id21710
pubs.end-page368en_NZ
pubs.finish-date2011-12-01en_NZ
pubs.start-date2011-11-29en_NZ


Files in this item

This item appears in the following Collection(s)

Show simple item record