A novel active learning strategy for domain adaptation in the classification of remote sensing images

Claudio Persello, Lorenzo Bruzzone

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

22 Citations (Scopus)

Abstract

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.
Original languageEnglish
Title of host publicationProceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2011), 24-29 July 2011, Vancouver, Canada. Washington, D.C. : IEEE, 2011. ISBN: 978-1-4577-1005-6. pp. 3720-3723
Place of PublicationWashington D.C., USA
PublisherIEEE
Pages3720-3723
ISBN (Electronic)978-1-4577-1005-6
ISBN (Print)978-1-4577-1003-2, 978-1-4577-1004-9 (CD)
DOIs
Publication statusPublished - 2011
Externally publishedYes

Publication series

NameIEEE International Geoscience and Remote Sensing Symposium (IGARSS)
PublisherIEEE
Volume2011
ISSN (Print)2153-6996
ISSN (Electronic)2153-7003

Keywords

  • ADLIB-ART-4711
  • n/a OA procedure

Fingerprint

Dive into the research topics of 'A novel active learning strategy for domain adaptation in the classification of remote sensing images'. Together they form a unique fingerprint.

Cite this