Graph Embedding and Distribution Alignment for Domain Adaptation in Hyperspectral Image Classification

Recent studies in cross-domain classification have shown that discriminant information of both source and target domains is very important. In this article, we propose a new domain adaptation (DA) method for hyperspectral image (HSI) classification, called graph embedding distribution alignment (GEDA). GEDA uses the pseudo-label learning to learn interclass intraclass divergence matrices domains, which preserves local domains. Meanwhile, spatial spectral features HSI are used, subspace performed minimize differences between We perform DA tasks on Yancheng, Botswana, University Pavia, Center Shanghai Hangzhou data sets. Experimental results show performance proposed better than existing methods.