Active Learning of Very-High Resolution Optical Imagery with SVM: Entropy vs Margin Sampling
Details
Serval ID
serval:BIB_28DAB7D4BC19
Type
Inproceedings: an article in a conference proceedings.
Collection
Publications
Institution
Title
Active Learning of Very-High Resolution Optical Imagery with SVM: Entropy vs Margin Sampling
Title of the conference
Proceedings of the IEEE International Geoscience and Remote Sensing Symposium IGARSS, Boston, USA
Publisher
Institute of Electrical and Electronics Engineers Library
Organization
IEEE Conference Publications
ISBN
978-1-4244-2808-3
Publication state
Published
Issued date
2008
Volume
4
Pages
73-76
Language
english
Notes
Tuia2008h
Abstract
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
Create date
25/11/2013 18:18
Last modification date
20/08/2019 14:08
Usage data
