A Deep Curriculum Learner in an Active Learning Cycle for Polsar Image Classification

The integration of deep learning and active learning has achieved great success in polarimetric synthetic aperture radar (PolSAR) image classification. However, the training samples provided by the active learning approach are inade-quate to promote the performance of deep learning methods. Also, in the initial learning stages, querying a small amount of informative and complex samples, which are plagued by significant speckle noise, not only increases the risk of overfitting, but also makes the further annotations of less importance. To alleviate these problems, by utilization of curriculum learning (CL), we propose a novel classification method for PolSAR images, considering the complexity of informative samples before applying them to the deep learning model. Furthermore, we develop a new lightweight 3D convolutional neural network with high-level feature extraction ability while having a very low computational cost. Experimental results with the two PolSAR benchmark data sets of AIRSAR Flevoland and ESAR Oberpfaffenhofen indicate our proposed method achieved the state-of-the-art classification results with a significantly smaller amount of training data.