Large-Scale Image Classification Using Active Learning
- 19 June 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 11 (1) , 259-263
Abstract
In this letter, we show how active learning can be particularly promising for classifying remote sensing images at large scales. The classification model constructed on samples extracted from a limited region of the image, called source domain, exhibits generally poor accuracies when used to predict the samples of a different region, called target domain, due to possible changes in class distributions throughout the image. To alleviate this problem, we suggest selecting and labeling additional samples from the new domain in order to improve generalization capabilities of the model. We propose to implement an initialization strategy based on clustering before applying the traditional active learning method in order to cope with distribution changes and better explore the feature space of the target domain. Experiments on a MODIS dataset for the generation of a land-cover map at European scale show good capabilities of the proposed approach for this purpose.Keywords
This publication has 14 references indexed in Scilit:
- SVM-Based Boosting of Active Learning Strategies for Efficient Domain AdaptationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012
- Using active learning to adapt remote sensing image classifiersRemote Sensing of Environment, 2011
- A Survey of Active Learning Algorithms for Supervised Remote Sensing Image ClassificationIEEE Journal of Selected Topics in Signal Processing, 2011
- Support Vector Machine Active Learning Through Significance Space ConstructionIEEE Geoscience and Remote Sensing Letters, 2010
- Forest Cover Classification With MODIS Images in Northeastern AsiaIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2010
- A Multiobjective Genetic SVM Approach for Classification Problems With Limited Training SamplesIEEE Transactions on Geoscience and Remote Sensing, 2009
- An Active Learning Approach to Hyperspectral Data ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2008
- Analysis of time-series MODIS 250 m vegetation index data for crop classification in the U.S. Central Great PlainsRemote Sensing of Environment, 2007
- Segmentation of multispectral remote sensing images using active support vector machinesPattern Recognition Letters, 2004
- A training algorithm for optimal margin classifiers1992