Hyperspectral Classification with Gradient Based Active Learning

Although the hyperspectral image classification method based on convolutional neural network(CNN) has made great progress, the classification task with less training samples remains a challenging problem. Active learning technology is able to alleviate the problem above by improving the quality of labeled samples. In this paper, we propose to choose informative samples in gradient space, which considers both uncertainty and diversity in selection process. At each iteration, we performs clustering on gradient vector of network parameters corresponding to each sample and its predicted label, then the samples nearest to cluster centers are selected and labeled. Moreover, in order to alleviate the overfitting problem duing to less training samples in the early stage of active learning process, we utilize a two-branch network with shared feature extraction module to learn both supervised classification and unsupervised clustering knowledge. The proposed method is validated on widely used hyperspectral image data set, and achieves better performance.