PathMamba: 一种混合Mamba-Transformer模型用于卫星图像中拓扑一致的道路分割
PathMamba: A Hybrid Mamba-Transformer for Topologically Coherent Road Segmentation in Satellite Imagery
AI总结：
PathMamba通过结合Mamba和Transformer的优势，实现了卫星图像中高精度且拓扑连续的道路分割，同时保持计算效率。
摘要：
在卫星图像中实现高精度和拓扑连续性道路分割是应用于城市规划到灾害响应等领域的关键目标。最先进的方法通常依赖于视觉Transformer，它们在捕捉全局上下文方面表现出色，但其二次复杂度是高效部署的主要障碍，特别是对于资源受限平台上的现场处理。相比之下，新兴的状态空间模型如Mamba提供了线性时间效率，并且本质上适合建模长而连续的结构。我们提出这些架构有互补的优势。为此，我们引入了PathMamba，一种新的混合架构，将Mamba的顺序建模与Transformer的全局推理相结合。我们的设计战略性地使用Mamba块来追踪道路网络的连续性，保持拓扑结构，同时整合Transformer块以利用全局上下文进行特征细化。这种方法在不产生纯注意力模型的可扩展性成本的情况下，实现了拓扑更优的分割图。我们在DeepGlobe Road Extraction和马萨诸塞州道路数据集上的实验表明，PathMamba设定了新的最先进的水平。值得注意的是，它显著提高了拓扑连续性，如通过APLS度量标准测量，建立了新的基准，同时保持计算上具有竞争力。
英文摘要：
Achieving both high accuracy and topological continuity in road segmentation from satellite imagery is a critical goal for applications ranging from urban planning to disaster response. State-of-the-art methods often rely on Vision Transformers, which excel at capturing global context, yet their quadratic complexity is a significant barrier to efficient deployment, particularly for on-board processing in resource-constrained platforms. In contrast, emerging State Space Models like Mamba offer linear-time efficiency and are inherently suited to modeling long, continuous structures. We posit that these architectures have complementary strengths. To this end, we introduce PathMamba, a novel hybrid architecture that integrates Mamba's sequential modeling with the Transformer's global reasoning. Our design strategically uses Mamba blocks to trace the continuous nature of road networks, preserving topological structure, while integrating Transformer blocks to refine features with global context. This approach yields topologically superior segmentation maps without the prohibitive scaling costs of pure attention-based models. Our experiments on the DeepGlobe Road Extraction and Massachusetts Roads datasets demonstrate that PathMamba sets a new state-of-the-art. Notably, it significantly improves topological continuity, as measured by the APLS metric, setting a new benchmark while remaining computationally competitive.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
