L2,0-norm regularization based feature selection for very high resolution remote sensing images

This paper presents a ℓ_2,0-norm regularization based feature selection method to analyze very high resolution remote sensing imagery. The method tackles the feature selection problem based on a ℓ_2,1-norm based objective function and a ℓ_{2, 0}-norm equality constraint. The constrained optimization problem is solved by an efficient algorithm based on augmented Lagrangian method to figure out a stable local solution. Though the ℓ_{2, 0}-norm regularization based feature selection method should handle a non-convex and non-smooth problem, it outperforms the ℓ_2,1-norm regularization based approximate convex counterparts and state-of-art feature selection methods in light of classification accuracies by 1-NN and SVM classifiers. The experimental results demonstrate the effectiveness of the presented method in selecting features with great generalization capabilities.