用状态空间模型提升遥感多类别目标计数精度
Mamba-MOC: A Multicategory Remote Object Counting via State Space Model
- 基于Mamba构建新网络，线性复杂度捕捉全局依赖
- 跨尺度交互模块融合多层特征，提升计数准确性
- 首个将Mamba用于遥感目标计数的方法，适合遥感应用
多类别遥感目标计数是计算机视觉中的基础任务，旨在准确估计遥感图像中各类物体的数量。现有方法依赖卷积神经网络（CNN）和变压器（Transformer），但CNN难以捕捉全局依赖，而Transformer计算开销大，限制了其在遥感场景中的应用。近期，Mamba在计算机视觉领域展现出潜力，能以线性复杂度建模全局依赖。为此，我们提出Mamba-MOC，一种基于Mamba的多类别遥感目标计数网络，首次将Mamba应用于遥感目标计数任务。具体而言，我们设计了跨尺度交互模块，促进层次化特征的深度融合；并引入上下文状态空间模型，同时捕获全局与局部上下文信息，并在扫描过程中提供局部邻域信息。在大规模真实场景下的实验结果表明，所提方法相比主流计数算法达到最先进性能。
原文摘要 · Abstract (English)
Multicategory remote object counting is a fundamental task in computer vision, aimed at accurately estimating the number of objects of various categories in remote images. Existing methods rely on CNNs and Transformers, but CNNs struggle to capture global dependencies, and Transformers are computationally expensive, which limits their effectiveness in remote applications. Recently, Mamba has emerged as a promising solution in the field of computer vision, offering a linear complexity for modeling global dependencies. To this end, we propose Mamba-MOC, a mamba-based network designed for multi-category remote object counting, which represents the first application of Mamba to remote sensing object counting. Specifically, we propose a cross-scale interaction module to facilitate the deep integration of hierarchical features. Then we design a context state space model to capture both global and local contextual information and provide local neighborhood information during the scan process. Experimental results in large-scale realistic scenarios demonstrate that our proposed method achieves state-of-the-art performance compared with some mainstream counting algorithms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。