GLDMamba: Global–Local Differential Mamba Network for Hyperspectral Image Change Detection (opens in new tab)

Convolutional neural networks (CNNs) and transformer-based methods have achieved significant progress in hyperspectral image (HSI) change detection (CD). However, most existing approaches adopt patch-based frameworks, which limit the effective utilization of full bitemporal HSI information. Moreover, CNNs struggle to capture long-range dependencies, while transformers incur high computational complexity. To address these limitations, this article proposes a global–local differential Mamba (GL...