dc.contributor.author | Werneck, Rafael de Oliveira | |
dc.contributor.author | Raveaux, Romain | |
dc.contributor.author | Tabbone, Salvatore | |
dc.contributor.author | Torres, Ricardo Da Silva | |
dc.date.accessioned | 2020-03-16T11:34:38Z | |
dc.date.available | 2020-03-16T11:34:38Z | |
dc.date.created | 2020-02-18T15:20:27Z | |
dc.date.issued | 2019 | |
dc.identifier.citation | Pattern Recognition Letters. 2019, 128 8-15. | nb_NO |
dc.identifier.issn | 0167-8655 | |
dc.identifier.uri | http://hdl.handle.net/11250/2646948 | |
dc.description.abstract | In several pattern recognition problems, effective graph matching is of paramount importance. In this paper, we introduce a novel framework to learn discriminative cost functions. These cost functions are embedded into a graph matching-based classifier. The learning algorithm is based on an open-set recognition approach. An open-set recognition describes a problem formulation in which the training process does not have access to labeled samples of all classes that may show up during the test phase. We also investigate a set of measures to characterize local graph properties. Performed experiments considering widely used datasets demonstrate that our solution leads to better or comparable results to those observed for several state-of-the-art baselines. | nb_NO |
dc.language.iso | eng | nb_NO |
dc.publisher | Elsevier | nb_NO |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internasjonal | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/deed.no | * |
dc.title | Learning cost function for graph classification with open-set methods | nb_NO |
dc.type | Journal article | nb_NO |
dc.type | Peer reviewed | nb_NO |
dc.description.version | acceptedVersion | nb_NO |
dc.source.pagenumber | 8-15 | nb_NO |
dc.source.volume | 128 | nb_NO |
dc.source.journal | Pattern Recognition Letters | nb_NO |
dc.identifier.doi | 10.1016/j.patrec.2019.08.010 | |
dc.identifier.cristin | 1795449 | |
dc.description.localcode | © 2019. This is the authors’ accepted and refereed manuscript to the article. Locked until 7.8.2021 due to copyright restrictions. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/ | nb_NO |
cristin.unitcode | 194,63,55,0 | |
cristin.unitname | Institutt for IKT og realfag | |
cristin.ispublished | true | |
cristin.fulltext | postprint | |
cristin.qualitycode | 1 | |