Active Learning of Very-High Resolution Optical Imagery with SVM: Entropy vs Margin Sampling
Devis Tuia, Frédéric Ratle, Fabio Pacifici, Alexei Pozdnoukhov, Mikhaïl Kanevski, Fabio Del Frate, D. Solimini, William J. Emery · 2008
An active learning method is proposed for the semi-automatic selection of training sets in remote sensing image classification. The method adds iteratively to the current training set the unlabeled pixels for which the prediction of an ensemble of classifiers based on bagged training sets show maximum entropy. This way, the algorithm selects the pixels that are the most uncertain and that will improve the model if added in the training set. The user is asked to label such pixels at each iteration. Experiments using support vector machines (SVM) on an 8 classes QuickBird image show the excellent performances of the methods, that equals accuracies of both a model trained with ten times more pixels and a model whose training set has been built using a state-of-the-art SVM specific active learning method.