BTCDNet: Bayesian Tile Attention Network for Hyperspectral Image Change Detection

Hyperspectral images (HSIs) provide detailed spectral information, which are effective for change detection (CD). Prior knowledge has been proven to improve the robustness of models in HSI processing. However, current CD methods do not fully use prior knowledge, and research on hyperspectral mangroves’ CD is limited. In this letter, we propose a general hyperspectral CD model with Bayesian prior guided module (BPGM) and tile attention block (TAB) called BTCDNet. BPGM leverages prior information to steer the model training process under limited labeled samples condition, while TAB can reduce complexity and improve performance by tile attention. Moreover, a novel and restricted hyperspectral CD dataset Shenzhen has been annotated for hyperspectral mangroves’ CD reference. Experiments demonstrate that our proposal achieves state-of-the-art (SOTA) performances on this dataset and two other public benchmark datasets. Our code and datasets are available at https://github.com/JeasunLok/BTCDNet