MCAFNet: Multiscale Cross-Attention Fusion Network for HSI and LiDAR Data Joint Classification (opens in new tab)

Hyperspectral images (HSIs) and light detection and ranging (LiDAR) data provide complementary spatial–spectral and elevation information, respectively, which can significantly enhance land cover classification. However, existing methods are often limited by shallow cross-modal interactions and static architectures that struggle with multiscale complex scenes. This article proposes a multiscale cross-attention fusion network (MCAFNet) for joint classification of HSI and LiDAR data. To address...