Convolutional Transformer-Based Few-Shot Learning for Cross-Domain Hyperspectral Image Classification

In cross-domain hyperspectral image (HSI) classification, the labeled samples of target domain are very limited, and it is a worthy attention to obtain sufficient class information from source categorize classes (both same new unseen classes). This article investigates this problem by employing few-shot learning (FSL) in meta-learning paradigm. However, most existing FSL methods extract statistical features based on convolutional neural networks (CNNs), which typically only consider local spatial among features, while ignoring global information. To make up for these shortcomings, proposes novel transformer-based (CTFSL). Specifically, first performed domains simultaneously build consistent scenario. Then, aligner set map dimensions. addition, transformer (CT) network utilized local-global features. Finally, discriminator executed subsequently that can not reduce shift but also distinguish feature originates. Experiments three widely used datasets indicate proposed CTFSL method superior state-of-the-art several typical HSI classification terms accuracy.