Abstract: Small object detection in remote sensing images faces challenges because of weak feature representation, complex background interference, and multi-scale variations. These challenges are more severe in resource-constrained environments, where both detection accuracy and model efficiency are required. This paper proposes an efficient detection framework named Multi-Scale Spatial Attention YOLO (MSSA-YOLO). The framework uses three lightweight modules to improve performance. The Hierarchical Feature Block (HFBlock) enhances small object features by dynamic scale selection and dual-axis multi-scale convolution. The Lightweight Downsampling Module (LDSample) applies efficient downsampling with residual connections to retain critical information. The Focal-WIoU Loss refines bounding box regression by adaptive weighting and gradient suppression. Experiments are conducted on three public datasets, VEDAI, VisDrone2019, and AI-TD. MSSA-YOLO achieves mAP50 values of 0.754, 0.436, and 0.519. Compared with YOLOv11s, the parameter count is reduced by 8.9%, while detection accuracy improves by 7%, 4.4%, and 18.5%. The framework also outperforms advanced models such as SP-YOLOv8s and SMN-YOLO. The results show that MSSA-YOLO achieves a balanced trade-off between accuracy and efficiency. The method is suitable for real-time small object detection and generalizes well to objects of different scales in remote sensing scenarios.

摘要： 遥感图像中的小目标检测由于特征表征能力不足、复杂背景干扰以及多尺度变化显著而面临较大挑战，尤其在资源受限的应用环境下，更需要在检测精度与模型复杂度之间实现有效平衡。针对这一问题，提出了一种高效的小目标检测框架——多尺度空间注意力YOLO（MSSA-YOLO）。首先使用自主设计的层次化特征模块（HFBlock），通过动态尺度选择和双轴多尺度卷积机制增强小目标的特征表征能力；其次设计轻量化下采样模块（LDSample），结合高效下采样与残差连接技术，在降低计算量的同时尽可能保留小目标的重要特征信息；最后引入Focal-WIoU损失函数，通过自适应加权和梯度抑制机制优化边界框回归过程，从而进一步提升检测精度。在VEDAI、VisDrone2019和AI-TOD三个公开数据集上的实验结果表明，MSSA-YOLO分别实现了0.754、0.436和0.519的mAP50指标，相较于基线模型YOLOv11s，在参数量减少8.9%的同时，mAP50分别提升7%、4.4%和18.5%。此外，与SP-YOLOv8s和SMN-YOLO等先进检测模型的对比实验显示，MSSA-YOLO在检测精度和模型效率上均取得较为明显的优势。结果表明，该方法不仅适用于小目标检测任务，还在不同尺度目标的检测中表现出较强的泛化能力，能够在资源受限和实时处理场景下提供一种可行的解决方案。