Cross-Domain Self-Taught Network for Few-Shot Hyperspectral Image Classification

In recent years, deep learning models, which possess powerful feature extraction abilities, have achieved remarkable success in the classification of hyperspectral images (HSIs). Nevertheless, a common challenge faced by most deep learning models, including few-shot learning (FSL) models, is the scarcity of valid labeled samples. To address this issue, we propose a cross-domain self-taught network (CDSTN) for few-shot HSI classification. The proposed CDSTN merges domain adaptation (DA) and semisupervised self-taught strategy to implement the FSL, which utilizes adequate labeled and unlabeled samples from source as well as target domains, respectively. For the feature information extraction of HSI, we propose a deep spatial–spectral feature embedded extractor composed of four residual blocks and a channel attention module (CAM). Additionally, a set of domain classifiers are introduced behind each residual block for the purpose of domain alignment by extracting more domain information at different depths of the network. Finally, plenty of unlabeled samples are assigned with pseudo labels through the trained network, and a pseudo label refinement (PLR) module is designed to select the most confident pseudo label sample for each class to further enrich the labeled database of target domain. Experiments conducted on four widely used benchmark HSI datasets demonstrate that CDSTN can obtain superior and stable performance with limited labeled samples compared with some state of the arts.