FastSAM-CD: Remote Sensing Image Change Detection Using Vision Foundation Models With Stronger Encoder and Decoder

Remote sensing image change detection (RSICD) is a crucial technique for Earth observation. However, the mainstream RSICD methods still face two main challenges. First, the encoding stage often fails to capture fine-grained structural representations, particularly in scenarios involving cross-scale targets and complex boundaries. Second, the decoding stage lacks effective modeling of spectral heterogeneity and direction-sensitive channel interactions, which severely limits the ability to accurately recognize strip-shaped objects. To address these issues, this paper proposes a network for RSICD named FastSAM-CD, which extends FastSAM with two dedicated modules. First, we design a hyperfusion multi-view adapter (HFM Adapter) for the encoder of FastSAM-CD. It significantly enhances the model’s ability to capture fine-grained boundaries across scales by constructing multi-view paths in both spatial-channel and local-global dimensions. Second, we propose a spectral-axial dynamic modulation module (SDM Module) for the decoder. It enhances the decoder’s extraction of spatial-frequency domain information through axial sensing and frequency-domain analysis, significantly improving the model’s detection accuracy for strip-shaped objects. The experiments on three RSICD datasets demonstrate that the proposed method outperforms the existing mainstream RSICD methods in terms of accuracy and efficiency.