Using active learning to adapt remote sensing image classifiers

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.

[1]  Luis Gómez-Chova,et al.  Semisupervised Image Classification With Laplacian Support Vector Machines , 2008, IEEE Geoscience and Remote Sensing Letters.

[2]  Jocelyn Chanussot,et al.  Decision Fusion for the Classification of Hyperspectral Data: Outcome of the 2008 GRS-S Data Fusion Contest , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Lawrence O. Hall,et al.  Active learning to recognize multiple types of plankton , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[4]  Michele Volpi,et al.  Unbiased query-by-bagging active learning for VHR image classification , 2010, Remote Sensing.

[5]  Sankar K. Pal,et al.  Segmentation of multispectral remote sensing images using active support vector machines , 2004, Pattern Recognit. Lett..

[6]  Lorenzo Bruzzone,et al.  Toward the Automatic Updating of Land-Cover Maps by a Domain-Adaptation SVM Classifier and a Circular Validation Strategy , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Gustavo Camps-Valls,et al.  Semisupervised Remote Sensing Image Classification With Cluster Kernels , 2009, IEEE Geoscience and Remote Sensing Letters.

[8]  Marin Ferecatu,et al.  Interactive Remote-Sensing Image Retrieval Using Active Relevance Feedback , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Rong Yan,et al.  Cross-domain video concept detection using adaptive svms , 2007, ACM Multimedia.

[10]  William J. Emery,et al.  Classification of Very High Spatial Resolution Imagery Using Mathematical Morphology and Support Vector Machines , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Lorenzo Bruzzone,et al.  Unsupervised retraining of a maximum likelihood classifier for the analysis of multitemporal remote sensing images , 2001, IEEE Trans. Geosci. Remote. Sens..

[12]  Xiaowei Xu,et al.  Representative Sampling for Text Classification Using Support Vector Machines , 2003, ECIR.

[13]  R. M. Hoffer,et al.  Computer-Aided Analysis of Landsat-1 MSS Data: A Comparison of Three Approaches, Including a "Modified Clustering" Approach-1 MSS Data: A Comparison of Three Approaches, Including a "Modified Clustering" Approach , 1975 .

[14]  Lorenzo Bruzzone,et al.  Mean Map Kernel Methods for Semisupervised Cloud Classification , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Johannes R. Sveinsson,et al.  Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles , 2008, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[16]  Klaus-Robert Müller,et al.  Covariate Shift Adaptation by Importance Weighted Cross Validation , 2007, J. Mach. Learn. Res..

[17]  Arnold W. M. Smeulders,et al.  Active learning using pre-clustering , 2004, ICML.

[18]  G. Foody,et al.  Predictive relations of tropical forest biomass from Landsat TM data and their transferability between regions , 2003 .

[19]  Antonio J. Plaza,et al.  Semisupervised Hyperspectral Image Segmentation Using Multinomial Logistic Regression With Active Learning , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[20]  William J. Emery,et al.  Active Learning Methods for Remote Sensing Image Classification , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[21]  John A. Richards,et al.  Cluster-space representation for hyperspectral data classification , 2002, IEEE Trans. Geosci. Remote. Sens..

[22]  Farid Melgani,et al.  Support Vector Machine Active Learning Through Significance Space Construction , 2011, IEEE Geoscience and Remote Sensing Letters.

[23]  Lawrence Carin,et al.  Detection of Unexploded Ordnance via Efficient Semisupervised and Active Learning , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[24]  Curtis E. Woodcock,et al.  Monitoring large areas for forest change using Landsat: Generalization across space, time and Landsat sensors , 2001 .

[25]  Pierre Soille,et al.  Morphological Image Analysis , 1999 .

[26]  Leszek Wojnar,et al.  Image Analysis , 1998 .

[27]  Lorenzo Bruzzone,et al.  A Fast Cluster-Assumption Based Active-Learning Technique for Classification of Remote Sensing Images , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[28]  Conghe Song,et al.  Forest mapping with a generalized classifier and Landsat TM data , 2001 .

[29]  Joydeep Ghosh,et al.  An Active Learning Approach to Hyperspectral Data Classification , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Neil D. Lawrence,et al.  Dataset Shift in Machine Learning , 2009 .

[31]  David A. Cohn,et al.  Improving generalization with active learning , 1994, Machine Learning.

[32]  Gunnar Rätsch,et al.  An Empirical Analysis of Domain Adaptation Algorithms for Genomic Sequence Analysis , 2008, NIPS.

[33]  Yasuharu Koike,et al.  Application of Covariate Shift Adaptation Techniques in Brain–Computer Interfaces , 2010, IEEE Transactions on Biomedical Engineering.

[34]  Qiong Jackson,et al.  An adaptive classifier design for high-dimensional data analysis with a limited training data set , 2001, IEEE Trans. Geosci. Remote. Sens..

[35]  Farid Melgani,et al.  Active Learning Methods for Electrocardiographic Signal Classification , 2010, IEEE Transactions on Information Technology in Biomedicine.

[36]  Steffen Bickel,et al.  Discriminative Learning Under Covariate Shift , 2009, J. Mach. Learn. Res..

[37]  Sanjoy Dasgupta,et al.  Hierarchical sampling for active learning , 2008, ICML '08.

[38]  Yue Gao,et al.  Semi-supervised Remote Sensing Image Segmentation Using Dynamic Region Merging , 2013, HCI.

[39]  Lorenzo Bruzzone,et al.  Kernel methods for remote sensing data analysis , 2009 .

[40]  Belur V. Dasarathy,et al.  Decision fusion , 1994 .

[41]  Robert H. Fraser,et al.  Signature extension through space for northern landcover classification: A comparison of radiometric correction methods , 2005 .