Using active learning to adapt remote sensing image classifiers

D. Tuia*, E. Pasolli, W.J. Emery

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

167 Citations (Scopus)


The validity of training samples collected in field campaigns is crucial for the success of land use classification models. However, such samples often suffer from a sample selection bias and do not represent the variability of spectra that can be encountered in the entire image. Therefore, to maximize classification performance, one must perform adaptation of the first model to the new data distribution. In this paper, we propose to perform adaptation by sampling new training examples in unknown areas of the image. Our goal is to select these pixels in an intelligent fashion that minimizes their number and maximizes their information content. Two strategies based on uncertainty and clustering of the data space are considered to perform active selection. Experiments on urban and agricultural images show the great potential of the proposed strategy to perform model adaptation.

Original languageEnglish
Pages (from-to)2232-2242
Number of pages11
JournalRemote Sensing of Environment
Issue number9
Publication statusPublished - 15 Sept 2011
Externally publishedYes


  • Active learning
  • Covariate shift
  • Hyperspectral
  • Image classification
  • Remote sensing
  • VHR


Dive into the research topics of 'Using active learning to adapt remote sensing image classifiers'. Together they form a unique fingerprint.

Cite this