Semi-supervised Remote Sensing Image Classification via Maximum Entropy
PDF Web
Remote sensing image segmentation requires multi-category classification typically with limited number of labeled training samples. While semi-supervised learning (SSL) has emerged as a sub-field of machine learning to tackle the scarcity of labeled samples, most SSL algorithms to date have had trade-offs in terms of scalability and/or applicability to multi-categorical data. In this paper, we evaluate semi-supervised logistic regression (SLR), a recent information theoretic semi-supervised algorithm, for remote sensing image classification problems. SLR is a probabilistic discriminative classifier and a specific instance of the generalized maximum entropy framework with a convex loss function. Moreover, the method is inherently multi-class and easy to implement. These characteristics make SLR a strong alternative to the widely used semi-supervised variants of SVM for the segmentation of remote sensing images. We demonstrate the competitiveness of SLR in multispectral, hyperspectral and radar image classifica tion.
| Author(s): | Erkan, AN. and Camps-Valls, G. and Altun, Y. |
| Links: | |
| Journal: | Proceedings of the 2010 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2010) |
| Pages: | 313-318 |
| Year: | 2010 |
| Month: | September |
| Day: | 0 |
| Publisher: | IEEE |
| BibTeX Type: | Conference Paper (inproceedings) |
| Address: | Piscataway, NJ, USA |
| DOI: | 10.1109/MLSP.2010.5589199 |
| Event Name: | 2010 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2010) |
| Event Place: | Kittilä, Finland |
| Digital: | 0 |
| Electronic Archiving: | grant_archive |
| Institution: | Institute of Electrical and Electronics Engineers |
| Language: | en |
| Organization: | Max-Planck-Gesellschaft |
| School: | Biologische Kybernetik |
BibTeX
@inproceedings{6619,
title = {Semi-supervised Remote Sensing Image Classification via Maximum Entropy},
journal = {Proceedings of the 2010 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2010)},
abstract = {Remote sensing image segmentation requires multi-category classification typically with limited number of labeled training samples. While semi-supervised learning (SSL) has emerged as a sub-field of machine learning to tackle the scarcity of labeled samples, most SSL algorithms to date have had trade-offs in terms of scalability and/or applicability to multi-categorical data. In this paper, we evaluate semi-supervised logistic regression (SLR), a recent information theoretic semi-supervised algorithm, for remote sensing image classification problems. SLR is a probabilistic discriminative classifier and a specific instance of the generalized maximum entropy framework with a convex loss function. Moreover, the method is inherently multi-class and easy to implement. These characteristics make SLR a strong alternative to the widely used semi-supervised variants of SVM for the segmentation of remote sensing images. We demonstrate the competitiveness of SLR in multispectral, hyperspectral and radar image classifica
tion.},
pages = {313-318},
publisher = {IEEE},
organization = {Max-Planck-Gesellschaft},
institution = {Institute of Electrical and Electronics Engineers},
school = {Biologische Kybernetik},
address = {Piscataway, NJ, USA},
month = sep,
year = {2010},
author = {Erkan, AN. and Camps-Valls, G. and Altun, Y.},
doi = {10.1109/MLSP.2010.5589199},
month_numeric = {9}
}