Please use this identifier to cite or link to this item:
|Title:||Structured learning of tree potentials in CRF for image segmentation||Authors:||Liu, Fayao
|Keywords:||Engineering::Computer science and engineering
Conditional Random Fields
|Issue Date:||2017||Source:||Liu, 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.2017.2690453||Series/Report no.:||IEEE Transactions on Neural Networks and Learning Systems||Abstract:||We 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.||URI:||https://hdl.handle.net/10356/107576
|ISSN:||2162-237X||DOI:||http://dx.doi.org/10.1109/TNNLS.2017.2690453||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.||Fulltext Permission:||open||Fulltext Availability:||With Fulltext|
|Appears in Collections:||SCSE Journal Articles|
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.