Visualization-Based Active Learning for the Annotation of SAR Images
Authors:
- 23 January 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 8 (10) , 4687-4698
Abstract
Active learning has gained a high amount of attention due to its ability to label a vast amount of unlabeled collected earth observation (EO) data. In this paper, we propose a novel active learning algorithm which is mainly based on employing a low-rank classifier as the training model and introducing a visualization support data point selection, namely, first certain wrong labeled (FCWL). The training model is composed of the logistic regression loss function and the trace-norm of learning parameters as regularizer. FCWL selects those data points whose labels are predicted wrong but the classifier is highly certain about them. Our experimental results performed on different extracted features from a dataset of SAR images confirm at least 10% improvement over the state-of-the-art methods.Keywords
Funding Information
- Munich Aerospace
This publication has 28 references indexed in Scilit:
- A cluster-assumption based batch mode active learning techniquePattern Recognition Letters, 2012
- Manifold Adaptive Experimental Design for Text CategorizationIEEE Transactions on Knowledge and Data Engineering, 2011
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- Active Learning Based on Locally Linear ReconstructionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Locally non-negative linear structure learning for interactive image retrieval2009
- Active learning in very large databasesMultimedia Tools and Applications, 2006
- Active learning via transductive experimental design2006
- Matrix Preconditioning Techniques and Applications2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- An Introduction to Support Vector Machines and Other Kernel-based Learning Methods2000