CTF-Net: A Convolutional and Transformer Fusion Network for SAR Ship Detection.

Synthetic aperture radar (SAR) is an active remote sensing system that possesses characteristics such as all-weather capability and strong penetrability. In ship detection, SAR is widely used in military and civilian applications due to its excellent properties. However, in practical applications, SAR often faces challenges in achieving ideal imaging results due to factors such as height and sea conditions. Although deep learning-based object detection methods have achieved promising results in SAR ship detection, the small size of ship targets and complex sea clutter makes it difficult to further improve the precision and recall rates of such algorithms. To address the challenge of balancing global and local features using convolution-based algorithms, this letter proposes a detection algorithm that integrates convolution and transformers. First, an improved transformer module is designed, which fuses the output feature maps of the traditional convolution module and the improved transformer module through a parallel structure. Then, a novel backbone structure is developed by stacking the aforementioned parallel structures, enabling the integration of global and local features as well as the detection of multiscale features. Experimental results demonstrate that compared to other models, the proposed method achieves more effective SAR detection in SAR images.