Consistency Regularization Semisupervised Learning for PolSAR Image Classification

Abstract

Polarimetric Synthetic Aperture Radar (PolSAR) images have emerged as an important data source for land cover classification research due to their all-weather, all-day monitoring capabilities. Deep learning-based classification methods have recently gained significant attention in PolSAR image classification since they have demonstrated excellent performance in the computer vision field. However, the main issue with deep learning-based methods is that they require large amounts of training data. Additionally, the scarcity of labeled data is a significant challenge in the PolSAR image field. Therefore, in this article, we proposed an advanced semisupervised deep self-training algorithm for PolSAR image classification, which utilized both labeled and unlabeled data in a semisupervised way. Then, a training optimization method and a high-confidence sample selection strategy are proposed by integrating consistency regularization. In addition, to achieve stronger feature extraction capabilities, we designed a deep learning-based classifier that combines residual blocks with an efficient multiscale attention module. We have conducted experiments on three popular real PolSAR datasets: 1989 Flevoland, 1991 Flevoland, and Oberpfaffenhofen. The classification results on these datasets demonstrated that the proposed method outperforms several other comparison algorithms, with overall accuracy up to 99.3%, 99.15%, and 94.12%, respectively. These results demonstrated the effectiveness of the proposed method for PolSAR image classification.