Multiscale Spectral-Morpho Fusion-Based Unsupervised Cross-Domain Learning for Hyperspectral Classification

Hyperspectral image classification (HSIC) plays a key role in remote sensing, but the interpretation of scene features with limited samples remains challenging. In this paper, we propose a multi-scale spectral morphological fusion network (MSMFNet) for unsupervised domain adaptation (UDA) in hyperspectral image classification. This method consists of several key steps. First, the network uses principal component analysis (PCA) to extract spectral features, which are then combined with extended morphological profiles (EMP) to enhance spatial structure representation. Then, a multi-scale heterogeneous feature aggregation (MHFA) module is introduced to capture heterogeneous features across different scales and directions. Next, the multi-scale global attention (MGA) module generates multi-level responses, exploring correlations between local and global information, thereby improving the representation of fine-grained features and boosting cross-domain feature fusion and classification performance. Finally, contrastive learning is applied to efficiently extract domain-invariant features. Experimental results demonstrate that MSMFNet achieves superior performance in cross-domain adaptation and fine-grained feature discrimination, achieving accuracies of 77.48% on the Houston dataset and 93.66% on the Pavia dataset, with Kappa coefficients that exceed the state-of-the-art by 2.46 and 2.48, respectively.