Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/107576
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLiu, Fayaoen
dc.contributor.authorLin, Guoshengen
dc.contributor.authorQiao, Ruizhien
dc.contributor.authorShen, Chunhuaen
dc.date.accessioned2019-11-05T01:36:20Zen
dc.date.accessioned2019-12-06T22:34:38Z-
dc.date.available2019-11-05T01:36:20Zen
dc.date.available2019-12-06T22:34:38Z-
dc.date.issued2017en
dc.identifier.citationLiu, F., Lin, G., Qiao, R., & Shen, C. (2018). Structured learning of tree potentials in CRF for image segmentation. IEEE Transactions on Neural Networks and Learning Systems, 29(6), 2631-2637. doi:10.1109/TNNLS.2017.2690453en
dc.identifier.issn2162-237Xen
dc.identifier.urihttps://hdl.handle.net/10356/107576-
dc.description.abstractWe propose a new approach to image segmentation, which exploits the advantages of both conditional random fields (CRFs) and decision trees. In the literature, the potential functions of CRFs are mostly defined as a linear combination of some predefined parametric models, and then, methods, such as structured support vector machines, are applied to learn those linear coefficients. We instead formulate the unary and pairwise potentials as nonparametric forests-ensembles of decision trees, and learn the ensemble parameters and the trees in a unified optimization problem within the large-margin framework. In this fashion, we easily achieve nonlinear learning of potential functions on both unary and pairwise terms in CRFs. Moreover, we learn classwise decision trees for each object that appears in the image. Experimental results on several public segmentation data sets demonstrate the power of the learned nonlinear nonparametric potentials.en
dc.format.extent10 p.en
dc.language.isoenen
dc.relation.ispartofseriesIEEE Transactions on Neural Networks and Learning Systemsen
dc.rights© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TNNLS.2017.2690453.en
dc.subjectEngineering::Computer science and engineeringen
dc.subjectDecision Treesen
dc.subjectConditional Random Fieldsen
dc.titleStructured learning of tree potentials in CRF for image segmentationen
dc.typeJournal Articleen
dc.contributor.schoolSchool of Computer Science and Engineeringen
dc.identifier.doi10.1109/TNNLS.2017.2690453en
dc.description.versionAccepted versionen
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:SCSE Journal Articles
Files in This Item:
File Description SizeFormat 
Structured Learning of Tree Potentials in CRF.pdf1.45 MBAdobe PDFThumbnail
View/Open

SCOPUSTM   
Citations 20

18
Updated on Mar 22, 2024

Web of ScienceTM
Citations 20

19
Updated on Oct 28, 2023

Page view(s)

323
Updated on Mar 28, 2024

Download(s) 50

99
Updated on Mar 28, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.