目目的 合成孔径雷达（Synthetic Aperture Radar, SAR）是一种主动式微波传感器，能够获取高分辨率的遥感图像，在海上船舶检测中至关重要。然而，SAR船舶检测主要面临两个挑战：复杂背景和船舶目标尺寸的多样性。为此，本文提出了适用于SAR船舶检测的多粒度上下文网络。方法 首先，设计了多粒度通道注意力（Multi-granularity Channel Attention, MCA）模块，对全局和局部的不同粒度的上下文信息进行加权，以增强对船舶目标重要信息的关注，降低复杂背景对检测结果的干扰。然后，设计了多粒度空洞自适应空间特征融合（Multi-granularity Atrous Adaptive Spatial Feature Fusion, MAASFF） 模块，采用自适应空间特征融合的方法，将三种不同扩张率（1、2和3）的空洞卷积提取的特征图进行融合，以减少特征图生成中的上下文信息损失，增强特征金字塔的表示能力，从而提高不同尺寸船舶的检测效果。结果 实验结果表明，本文方法在SAR-Ship-Dataset和SSDD两个数据集上与其他9种方法进行比较均取得最佳的检测结果，平均精度分别达到了96.1%和97.0%，进一步验证了该网络在SAR船舶检测任务中出色的性能表现。结论 本文提出了一种多粒度上下文网络，旨在抑制复杂背景干扰并增强对多尺寸船舶特征的提取能力，有效提高了SAR船舶检测的准确性。

Objective Synthetic aperture radar (SAR), as an active microwave sensor, can acquire high-resolution remote sensing images, which is crucial in marine ship detection. Nevertheless, there are two primary challenges confronting ship detection in SAR images. First and foremost, SAR images frequently encompass complex backgrounds, incorporating turbulent sea waves, islands, and various forms of clutter. These complex backgrounds can significantly hinder the accurate identification of ship targets. Moreover, the diverse spectrum of ship target sizes within SAR images presents another significant challenge. Traditional detection methods struggle to adapt to the broad range of ship sizes encountered in real-world scenarios. In recent years, with the extensive application of deep learning models and attention mechanisms, researchers have successfully improved the performance of SAR ship detection methods and effectively overcome the detection challenges of SAR ship targets of different sizes in complex backgrounds. However, these methods either have limitations in detection accuracy or require extensive computing resources. To address these challenges, this paper proposes a multi-granularity context network for SAR ship detection. Method First, a Multi-granularity Channel Attention (MCA) module is designed to weight the global and local contextual information of different granularities. The primary function of the MCA module is to focus on important characteristics of ship targets and minimize interference caused by complex backgrounds on detection results. To further lightweight the MCA module, pointwise convolution replaces traditional convolution as an aggregator of global and local channel context information. This substitution not only trims computational overhead but also streamlines the process. Furthermore, the MCA module is integrated into the first layer of the backbone network feature extraction of the YOLOv5s framework. The fusion of pointwise convolution and integration within the network architecture collectively strengthens our capability for accurate and efficient SAR ship detection. Then, a Multi-granularity Atrous Adaptive Spatial Feature Fusion (MAASFF) module is designed to reduce the loss of contextual information in feature map generation and enhance the representation capability of feature pyramids, thereby improving the detection performance of ships at different sizes. In addition, within the process of fusing features of different granularities, the MAASFF module avoids ignoring the differences between ship target features of different sizes and reduces unnecessary computational overload. Its primary employs an adaptive spatial feature fusion method to merge the feature maps extracted using three different atrous rates (1, 2, and 3) of atrous convolutions. This design effectively captures features at different spatial granularities, enhancing the feature representation capability for ships of different sizes. Result Compared with nine other methods on two datasets, SAR-Ship-Dataset and SSDD, our method achieves the best detection results. On the SAR-Ship-Dataset, compared with the two-stage methods Faster R-CNN, DAPN, CR2A-Net, KCPNet, and BL-Net, our method can improve model detection accuracy by approximately 1.9% to 6.0%. Compared to common one-stage methods such as YOLOv4, CenterNet++, CRDet, and YOLOv5s, our method can enhance performance by 2.9%, 1.2%, 0.9%, and 1.8%, respectively. Experimental results indicate that our method achieves the best performance on SAR-Ship-Dataset, reaching 96.1% mAP, outperforming all compared methods. On the SSDD dataset, our method improves the performance by approximately 8.7% (Faster R-CNN), 6.9% (DAPN), 7.2% (CR2A-Net), 4.5% (KCPNet), 1.8% (BL-Net), 0.9% (YOLOv4), 4.3% (CenterNet++), 0.6% (CRDet), and 1.6% (YOLOv5s), while maintaining a speed similar to the baseline YOLOv5s. These results show our method has good generalization ability and reaches the best performance with 97.0% mAP. It further verifies the excellent effect and performance of our method in SAR ship detection tasks. Conclusion This paper proposes a multi-granularity context network, which aims to suppress complex background interference and enhance the ability to extract features of multi-sized ships, effectively improving the accuracy of SAR ship detection.