Online Submission!

Open Journal Systems


U.Pushpa Lingam


Interactive Domain Adaptation (IDA) technique based on active learning for the classification of remote sensing images. Interactive domain adaptation method is used for adapting the supervised classifier trained on a given remote sensing source image to make it suitable for classifying a different but related target image. The two images can be acquired in different locations and at different times. This method iteratively selects the most informative samples of the target image to be labeled and included in the training set and the source image samples are reweighted or removed from the training set on the basis of their disagreement with the target image classification problem. The consistent information available from the source image can be effectively exploited for the classification of the target image and for guiding the selection of new samples to be labeled, whereas the inconsistent information is automatically detected and removed. This approach significantly reduces the number of new labeled samples to be collected from the target image. Experimental results on both a multispectral very high resolution and a hyper spectral data set confirm the effectiveness of the interactive domain adaptation for theclassification of remote sensing using active learning method.

Full Text:



P. Mitra, B. U. Shankar, and S. K. Pal, “Segmentation of multispectral remote sensing images using active support vector machines,” PatternRecognit. Lett. vol. 25, no. 9, pp. 1067–1074, Jul. 2004.

S. Rajan, J. Ghosh, and M. Crawford, “An active learning approach tohyperspectral data classification,” IEEE Trans. Geosci. Remote Sens.,vol. 46, no. 4, pp. 1231–1242, Apr. 2008.

G. Jun and J. Ghosh, “An efficient active learning algorithm with knowledgetransfer for hyperspectral data analysis,” in Proc. IEEE IGARSS,Jul. 2008, vol. 1, pp. I-52–I-55.

B. Demir, C. Persello, and L. Bruzzone, “Batch-mode active-learningmethods for the interactive classification of remote sensing images,” IEEETrans. Geosci. Remote Sens., vol. 49, no. 3, pp. 1014–1031, Mar. 2011.

J. Huang, A. Gretton, B. Schölkopf, A. J. Smola, and K. M. Borgwardt,“Correcting sample selection bias by unlabeled data,” in Proc. Advancesin Neural Information Processing Systems. Cambridge,MA: MIT Press, 2007.

D. Tuia, E. Pasolli, and W. J. Emery, “Using active learning to adaptremote sensing image classifiers,” Remote Sens. Environ., vol. 115, no. 9, pp. 2232–2242, Sep. 2011.

W. Dai, Q. Yang, G. Xue, and Y. Yu, “Boosting for transfer learning,” inProc. Int. Conf. Mach. Learn., 2007, pp. 193–200.

C. Persello and L. Bruzzone, “Active learning for domain adaptation in thesupervised classification of remote sensing images,” IEEE Trans. Geosci.Remote Sens., vol. 50, no. 11, pp. 4468–4483, Nov. 2012.

B. Schölkopf and A. J. Smola, Learning with Kernels: Support VectorMachines, Regularization, Optimization, and Beyond. Cambridge, MA: MIT Press, 2001.

F. Melgani and L. Bruzzone, “Classification of hyperspectral remote sensingimages with support vector machines,” IEEE Trans. Geosci. RemoteSens., vol. 42, no. 8, pp. 1778–1790, Aug. 2004.



  • There are currently no refbacks.

Copyright (c) 2015 COMPUSOFT "An International Journal of Advanced Computer Technology"