Hyperspectral Image Classification using Uncertainty and Diversity based Active Learning

Abstract

There has been extensive research in the field of Hyperspectral Image Classification using deep neural networks. The deep learning based approaches requires huge amount of labelled data samples. But in the case of Hyperspectral Image, there are less number of labelled data samples. Therefore, we can adopt Active Learning combined with deep learning based approaches to be able to extract most informative data samples. By using this technique, we can train the classifier to achieve better classification accuracies with less number of labelled data samples. There is considerable amount of research carried out for selecting diverse data samples from the pool of unlabeled data samples. We present a novel diversity-based Active Learning approach utilizing the information of clustered data distribution. We incorporate diversity criteria with Active Learning selection criteria and combine it with Convolutional Neural Network for feature extraction and classification. This approach helps us in obtaining most informative and diverse data samples. We have compared our proposed approach with three other sampling methods in terms of classification accuracies, Cohen Kappa score, which shows that our approach gives better results with comparison to other sampling methods.