Active Learning of Very-High Resolution Optical Imagery with SVM: Entropy vs Margin Sampling
Détails
ID Serval
serval:BIB_28DAB7D4BC19
Type
Actes de conférence (partie): contribution originale à la littérature scientifique, publiée à l'occasion de conférences scientifiques, dans un ouvrage de compte-rendu (proceedings), ou dans l'édition spéciale d'un journal reconnu (conference proceedings).
Collection
Publications
Institution
Titre
Active Learning of Very-High Resolution Optical Imagery with SVM: Entropy vs Margin Sampling
Titre de la conférence
Proceedings of the IEEE International Geoscience and Remote Sensing Symposium IGARSS, Boston, USA
Editeur
Institute of Electrical and Electronics Engineers Library
Organisation
IEEE Conference Publications
ISBN
978-1-4244-2808-3
Statut éditorial
Publié
Date de publication
2008
Volume
4
Pages
73-76
Langue
anglais
Notes
Tuia2008h
Résumé
An active learning method is proposed for the semi-automatic selection
of training sets in remote sensing image classification. The method
adds iteratively to the current training set the unlabeled pixels
for which the prediction of an ensemble of classifiers based on bagged
training sets show maximum entropy. This way, the algorithm selects
the pixels that are the most uncertain and that will improve the
model if added in the training set. The user is asked to label such
pixels at each iteration. Experiments using support vector machines
(SVM) on an 8 classes QuickBird image show the excellent performances
of the methods, that equals accuracies of both a model trained with
ten times more pixels and a model whose training set has been built
using a state-of-the-art SVM specific active learning method
of training sets in remote sensing image classification. The method
adds iteratively to the current training set the unlabeled pixels
for which the prediction of an ensemble of classifiers based on bagged
training sets show maximum entropy. This way, the algorithm selects
the pixels that are the most uncertain and that will improve the
model if added in the training set. The user is asked to label such
pixels at each iteration. Experiments using support vector machines
(SVM) on an 8 classes QuickBird image show the excellent performances
of the methods, that equals accuracies of both a model trained with
ten times more pixels and a model whose training set has been built
using a state-of-the-art SVM specific active learning method
Création de la notice
25/11/2013 18:18
Dernière modification de la notice
20/08/2019 14:08
Données d'usage
