BASeg：结合结构惩罚的边界感知遥感图像分割
BASeg: Boundary-Aware Remote Sensing Segmentation with Structural Penalties
浏览论文内容
中文总结 AI 辅助
针对遥感图像分割的边界细节不足等问题，本文提出含MABL损失与GSM、CFM模块的BASeg框架，构建GCD-25k数据集，在4个基准上最高提升mIoU达2.8%，性能优于现有方法。
中文摘要 AI 辅助
语义分割是遥感领域的核心计算机视觉任务，可推动城市发展、农业、生态、水资源及环境监测等领域的进步。然而，现有方法通常难以捕获细粒度目标特征与边界细节；此外，当前广泛使用的数据集往往缺乏城市形态多样性，且生成式图像的分割研究仍未得到充分探索。为解决这些问题，本文提出马氏距离-角度边界损失（Mahalanobis-Angle Boundary Loss, MABL），其可显式增强边界与形状一致性，通过基于马氏距离的加权及角度感知惩罚联合建模结构重要性与边界方向，且能便捷集成至各类分割架构中，持续提升其准确率。基于MABL，本文引入BASeg——一款结合结构惩罚的边界感知遥感图像分割框架，该框架集成全局视觉状态空间模块（Global Visual State Space module, GSM）与跨特征融合模块（Cross-Feature Fusion module, CFM），以捕获长程上下文依赖与细粒度局部细节。此外，本文构建含10座城市的基准数据集（GCD-25k），以助力精准的建筑与道路分割。在4个遥感基准数据集上开展的大量实验表明，BASeg在各类场景中均优于现有方法，在平均交并比（mIoU）上最高提升2.8%，且能生成更精准的目标边界分割结果；同时，将MABL集成至多类现有分割架构中可在各数据集上持续提升性能，证明其鲁棒性与广泛适用性。
英文摘要
Semantic segmentation is a core computer vision task in the remote sensing field, accelerating advancements in ur- ban development, agriculture, ecology, water resources, and environmental monitoring. However, recent methods usually struggle to capture fine-grained object features and bound- ary details. Besides, current widely used datasets often lack city morphology diversity and segmentation on generative im- ages remains largely unexplored. To address these issues, we propose a Mahalanobis-Angle Boundary Loss (MABL) that explicitly enhances boundary and shape consistency. MABL jointly models structural importance and boundary orientation through Mahalanobis distance-based weighting and angle- aware penalty. It can be readily integrated into diverse seg- mentation architectures and consistently improves their accu- racy. Built upon MABL, we introduce BASeg, a boundary- aware remote sensing segmentation framework with Struc- tural Penalties. BASeg integrates a Global Visual State Space module (GSM) with a Cross-Feature Fusion module (CFM) to capture both long-range contextual dependencies and fine- grained local details. Additionally, we establish a global 10- city benchmark dataset (GCD-25k) to facilitate accurate build- ing and road segmentation. Extensive experiments on four remote-sensing benchmarks demonstrate that BASeg consis- tently outperforms existing methods, achieving up to a 2.8% improvement in mIoU while producing more accurate object boundary segmentation across diverse scenes. Moreover, integrating MABL into multiple existing segmentation archi- tectures consistently improves performance across datasets, demonstrating its robustness and broad applicability.
