Header logo is ei

A Novel Active Learning Strategy for Domain Adaptation in the Classification of Remote Sensing Images

2011

Conference Paper

ei


We present a novel technique for addressing domain adaptation problems in the classification of remote sensing images with active learning. Domain adaptation is the important problem of adapting a supervised classifier trained on a given image (source domain) to the classification of another similar (but not identical) image (target domain) acquired on a different area, or on the same area at a different time. The main idea of the proposed approach is to iteratively labeling and adding to the training set the minimum number of the most informative samples from target domain, while removing the source-domain samples that does not fit with the distributions of the classes in the target domain. In this way, the classification system exploits already available information, i.e., the labeled samples of source domain, in order to minimize the number of target domain samples to be labeled, thus reducing the cost associated to the definition of the training set for the classification of the target domain. Experimental results obtained in the classification of a hyperspectral image confirm the effectiveness of the proposed technique.

Author(s): Persello, C. and Bruzzone, L.
Pages: 3720-3723
Year: 2011
Month: July
Day: 0
Publisher: IEEE

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

DOI: 10.1109/IGARSS.2011.6050033
Event Name: IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2011)
Event Place: Vancouver, BC, Canada

Address: Piscataway, NJ, USA
Digital: 0
ISBN: 978-1-4577-1003-2

Links: Web

BibTex

@inproceedings{PerselloB2011_2,
  title = {A Novel Active Learning Strategy for Domain Adaptation in the Classification of Remote Sensing Images},
  author = {Persello, C. and Bruzzone, L.},
  pages = {3720-3723 },
  publisher = {IEEE},
  address = {Piscataway, NJ, USA},
  month = jul,
  year = {2011},
  month_numeric = {7}
}