FSDENet: A Frequency and Spatial Domains based Detail Enhancement Network for Remote Sensing Semantic Segmentation
This addresses segmentation accuracy issues in remote sensing for applications like urban planning, but it is incremental as it builds on existing domain-specific methods.
The paper tackled semantic edge ambiguities in remote sensing image segmentation by proposing FSDENet, which integrates spatial and frequency-domain processing to enhance boundary details, achieving state-of-the-art performance on four datasets including LoveDA, Vaihingen, Potsdam, and iSAID.
To fully leverage spatial information for remote sensing image segmentation and address semantic edge ambiguities caused by grayscale variations (e.g., shadows and low-contrast regions), we propose the Frequency and Spatial Domains based Detail Enhancement Network (FSDENet). Our framework employs spatial processing methods to extract rich multi-scale spatial features and fine-grained semantic details. By effectively integrating global and frequency-domain information through the Fast Fourier Transform (FFT) in global mappings, the model's capability to discern global representations under grayscale variations is significantly strengthened. Additionally, we utilize Haar wavelet transform to decompose features into high- and low-frequency components, leveraging their distinct sensitivity to edge information to refine boundary segmentation. The model achieves dual-domain synergy by integrating spatial granularity with frequency-domain edge sensitivity, substantially improving segmentation accuracy in boundary regions and grayscale transition zones. Comprehensive experimental results demonstrate that FSDENet achieves state-of-the-art (SOTA) performance on four widely adopted datasets: LoveDA, Vaihingen, Potsdam, and iSAID.