Empirical Inference Conference Paper 2009

Active learning for classification of remote sensing images

Web
no image
Empirical Inference

This paper presents an analysis of active learning techniques for the classification of remote sensing images and proposes a novel active learning method based on support vector machines (SVMs). The proposed method exploits a query function for the inclusion of batches of unlabeled samples in the training set, which is based on the evaluation of two criteria: uncertainty and diversity. This query function adopts a stochastic approach to the selection of unlabeled samples, which is based on a function of uncertainty estimated from the distribution of errors on the validation set (which is assumed available for the model selection of the SVM classifier). Experimental results carried out on a very high resolution image confirm the effectiveness of the proposed active learning technique, which results more accurate than standard methods.

Author(s): Bruzzone, L. and Persello, C.
Links:
Pages: III-693-III-696
Year: 2009
Month: July
Day: 0
Publisher: IEEE
Bibtex Type: Conference Paper (inproceedings)
Address: Piscataway, NJ, USA
DOI: 10.1109/IGARSS.2009.5417857
Event Name: IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2009)
Event Place: Cape Town, South Africa
Digital: 0
Electronic Archiving: grant_archive
ISBN: 978-1-4244-3394-0

BibTex

@inproceedings{BruzzoneP2009_2,
  title = {Active learning for classification of remote sensing images },
  abstract = {This paper presents an analysis of active learning techniques for the classification of remote sensing images and proposes a novel active learning method based on support vector machines (SVMs). The proposed method exploits a query function for the inclusion of batches of unlabeled samples in the training set, which is based on the evaluation of two criteria: uncertainty and diversity. This query function adopts a stochastic approach to the selection of unlabeled samples, which is based on a function of uncertainty estimated from the distribution of errors on the validation set (which is assumed available for the model selection of the SVM classifier). Experimental results carried out on a very high resolution image confirm the effectiveness of the proposed active learning technique, which results more accurate than standard methods.},
  pages = {III-693-III-696 },
  publisher = {IEEE},
  address = {Piscataway, NJ, USA},
  month = jul,
  year = {2009},
  slug = {bruzzonep2009_2},
  author = {Bruzzone, L. and Persello, C.},
  month_numeric = {7}
}