TY - JOUR
T1 - Frequency-Spatial Dual-Path Modeling for Remote Sensing Image Semantic Segmentation
AU - Wang, Zhen
AU - Yuan, Shen Ao
AU - Li, Jiayuan
AU - Li, Ruixiang
AU - Xu, Nan
AU - You, Zhuhong
AU - Huang, Deshuang
N1 - Publisher Copyright:
© 1980-2012 IEEE.
PY - 2026
Y1 - 2026
N2 - Semantic segmentation of remote sensing images (RSIs) faces persistent challenges in high-frequency information degradation, boundary ambiguity, and structural inconsistency. To address these issues, we present a Frequency-Spatial Dual-Path Modeling (FSDPNet) paradigm that achieves holistic structural enhancement and fine-grained detail preservation. Specifically, we introduce a Frequency-Reduction Mamba Mechanism (FRMM), which explicitly disentangles and adaptively retains critical high-frequency and directional representations during encoding. In the decoding stage, a Multi-Scale Frequency-Driven Reconstruction Module (MFRM) leverages frequency-domain enhancement and dilated convolutions for progressive resolution recovery and precise texture compensation. Furthermore, a SAM (Segment Anything Model)-constrained Semantic Consistency Fusion Module (SCFM) harnesses structural priors to reinforce boundary delineation and suppress semantic ambiguity across scales. The overall training is guided by a composite objective that jointly optimizes global semantic consistency and local structural fidelity. Extensive experiments on multiple remote sensing benchmarks demonstrate that our approach consistently outperforms state-of-the-art segmentation methods, setting a new standard for structural integrity and fine-detail preservation in remote sensing image segmentation.
AB - Semantic segmentation of remote sensing images (RSIs) faces persistent challenges in high-frequency information degradation, boundary ambiguity, and structural inconsistency. To address these issues, we present a Frequency-Spatial Dual-Path Modeling (FSDPNet) paradigm that achieves holistic structural enhancement and fine-grained detail preservation. Specifically, we introduce a Frequency-Reduction Mamba Mechanism (FRMM), which explicitly disentangles and adaptively retains critical high-frequency and directional representations during encoding. In the decoding stage, a Multi-Scale Frequency-Driven Reconstruction Module (MFRM) leverages frequency-domain enhancement and dilated convolutions for progressive resolution recovery and precise texture compensation. Furthermore, a SAM (Segment Anything Model)-constrained Semantic Consistency Fusion Module (SCFM) harnesses structural priors to reinforce boundary delineation and suppress semantic ambiguity across scales. The overall training is guided by a composite objective that jointly optimizes global semantic consistency and local structural fidelity. Extensive experiments on multiple remote sensing benchmarks demonstrate that our approach consistently outperforms state-of-the-art segmentation methods, setting a new standard for structural integrity and fine-detail preservation in remote sensing image segmentation.
KW - boundary delineation
KW - Remote sensing
KW - semantic consistency
KW - semantic segmentation
KW - structure feature
UR - https://www.scopus.com/pages/publications/105053987844
U2 - 10.1109/TGRS.2026.3742393
DO - 10.1109/TGRS.2026.3742393
M3 - 文章
AN - SCOPUS:105053987844
SN - 0196-2892
JO - IEEE Transactions on Geoscience and Remote Sensing
JF - IEEE Transactions on Geoscience and Remote Sensing
ER -