2020/06/30 by Lamei Zhang, Siyu Zhang, Bin Zou +1 · 49 citations
Computer Science · Engineering · #Advanced SAR Imaging Techniques #Artificial intelligence #Artificial neural network #Computer science #Contextual image classification #Convolutional neural network #Deep learning #Geophysical Methods and Applications #Image (mathematics) #Machine learning #Overfitting #Pattern recognition (psychology) #Synthetic Aperture Radar (SAR) Applications and Techniques #cs.CV
paper · pdf · doi:10.1109/tgrs.2020.3043191
published in IEEE Transactions on Geoscience and Remote Sensing 60, 1-16 (Institute of Electrical and Electronics Engineers) · 16 pages, 16 figures
openalex publication_date 2020/12/22 · arxiv created 2020/12/25 · arxiv updated 2020/12/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Deep learning and convolutional neural networks (CNNs) have made progress in polarimetric synthetic aperture radar (PolSAR) image classification over the past few years. However, a crucial issue has not been addressed, i.e., the requirement of CNNs for abundant labeled samples versus the insufficient human annotations of PolSAR images. It is well known that following the supervised learning paradigm may lead to the overfitting of training data, and the lack of supervision information of PolSAR images undoubtedly aggravates this problem, which greatly affects the generalization performance of CNN-based classifiers in large-scale applications. To handle this problem, in this article, learning transferrable representations from unlabeled PolSAR data through convolutional architectures is explored for the first time. Specifically, a PolSAR-tailored contrastive learning network (PCLNet) is proposed for unsupervised deep PolSAR representation learning and few-shot classification. Different from the utilization of optical processing methods, a diversity stimulation mechanism is constructed to narrow the application gap between optics and PolSAR. Beyond the conventional supervised methods, PCLNet develops an unsupervised pretraining phase based on the proxy objective of instance discrimination to learn useful representations from unlabeled PolSAR data. The acquired representations are transferred to the downstream task, i.e., few-shot PolSAR classification. Experiments on two widely used PolSAR benchmark data sets confirm the validity of PCLNet. Besides, this work may enlighten how to efficiently utilize the massive unlabeled PolSAR data to alleviate the greedy demands of CNN-based methods for human annotations.