MoE-based Mamba for Multi-scene Universal Remote Sensing Semantic Segmentation

Remote sensing semantic segmentation (RSSS) aims to achieve pixel-level classification of remote sensing imagery for land cover identification. However, most existing RSSS methods are tailored for single-scene tasks and lack generalizability across diverse scenes. Extending these models to multi-scene tasks often results in decreased accuracy, increased training time and computational demands. In this paper, we propose MoE-SegMamba, a universal model for efficient multi-scene RSSS. Specifically, we propose an efficient encoder based on the novel TMoESSM Block, which includes a 2D Selective Scan module for capturing global information and a Task-aware Mixture-of-Experts (TMoE) Block to address multi-scene segmentation challenges. To mitigate task interference, we introduce the MoE Guidance Instructions (MGI) module, which generates task-related instructions to assist the TMoE Block in reducing spatial-dimension interference and support the Instruction Channel Gating Module (ICGM) in mitigating channel-dimension interference. Experimental results demonstrate that our proposed MoE-SegMamba achieves State-of-the-Art performance across four semantic segmentation scenes. The code is available at https://github.com/quanquans931225/MoE-SegMamba.