Please use this identifier to cite or link to this item:
Type: Artigo
Title: Learning cost function for graph classification with open-set methods
Author: Werneck, Rafael de Oliveira
Raveaux, Romain
Tabbone, Salvatore
Torres, Ricardo da Silva
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
Subject: Máquina de vetores de suporte
Country: Países Baixos
Editor: Elsevier
Rights: Fechado
Identifier DOI: 10.1016/j.patrec.2019.08.010
Date Issue: Dec-2019
Appears in Collections:IC - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
000498398400002.pdf1.25 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.