English

SAIP-Net: Enhancing Remote Sensing Image Segmentation via Spectral Adaptive Information Propagation

Computer Vision and Pattern Recognition 2025-10-15 v2 Graphics

Abstract

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.

Keywords

Cite

@article{arxiv.2504.16564,
  title  = {SAIP-Net: Enhancing Remote Sensing Image Segmentation via Spectral Adaptive Information Propagation},
  author = {Zhongtao Wang and Xizhe Cao and Yisong Chen and Guoping Wang},
  journal= {arXiv preprint arXiv:2504.16564},
  year   = {2025}
}
R2 v1 2026-06-28T23:08:19.698Z