MambaTriNet: A Mamba-Based Tribackbone Multimodal Remote Sensing Image Semantic Segmentation Model

Integrating digital surface models (DSMs) with remote sensing images has emerged as a pivotal strategy for remote sensing semantic segmentation. While prevailing dual-branch convolutional frameworks independently process DSM and remote sensing image, their inherent limitations in modeling long-range contextual dependencies persist due to convolutional operations' local receptive fields. Notably, the hierarchical feature in the U-model inherently embodies multiscale complementary relationships, yet current multimodal fusion paradigms insufficiently exploit this architectural advantage. In this letter, we propose an efficient three-branch structure encoder to simultaneously extract DSM features and local and global features of remote sensing images. Notably, we leverage the recently introduced Mamba instead of the Transformer to capture long-range dependencies, significantly reducing computational complexity while maintaining competitive performance. The extracted features are integrated using the trifeature complementary fusion (TriFusion) module, which employs a stepwise fusion strategy to learn the spatial complementarity between global and local features and channelwise complementarity between remote sensing images and DSM. In addition, we introduce a cross-layer feature guidance (CLFG) module within the skip connections to improve segmentation accuracy by facilitating enhanced cross-layer feature propagation. Extensive experiments conducted on two high-resolution remote sensing datasets, ISPRS Vaihingen and Potsdam datasets, demonstrate that the proposed MambaTriNet surpasses existing state-of-the-art methods in performance metrics, achieving 83.84% and 86.05% mean intersection over union (mIoU), respectively.