SAIP-Net: Enhancing Remote Sensing Image Segmentation via Spectral Adaptive Information Propagation
This work solves the challenge of achieving precise spatial boundaries and intra-class consistency in remote sensing image segmentation, which is incremental as it builds on existing frequency-aware and multi-scale approaches.
The paper tackled the problem of semantic segmentation in remote sensing imagery by addressing spatial domain feature fusion and insufficient receptive fields, resulting in significant performance improvements over state-of-the-art methods.
Semantic segmentation of remote sensing imagery demands precise spatial boundaries and robust intra-class consistency, challenging conventional hierarchical models. To address limitations arising from spatial domain feature fusion and insufficient receptive fields, this paper introduces SAIP-Net, a novel frequency-aware segmentation framework that leverages Spectral Adaptive Information Propagation. SAIP-Net employs adaptive frequency filtering and multi-scale receptive field enhancement to effectively suppress intra-class feature inconsistencies and sharpen boundary lines. Comprehensive experiments demonstrate significant performance improvements over state-of-the-art methods, highlighting the effectiveness of spectral-adaptive strategies combined with expanded receptive fields for remote sensing image segmentation.