DAMF-DETR:A Dual-Path Attention and Multi-Scale Frequency-Domain Awareness for Small Object Detection in Remote Sensing Images

With the rapid advancement of remote sensing technology, target detection in remote sensing imagery plays a crucial role in military reconnaissance, urban planning, and other fields. However, there are problems such as large variations in target scale, arbitrary angles, and complex background interference in remote sensing images, making it difficult for existing target detection methods to achieve precise recognition and localization. To address these issues, this article proposes a small target detection model for remote sensing images based on a dual-path attention mechanism and multiscale frequency domain awareness. First, we propose the GDSC module, a gated deep separable spatial convolution module that enhances the extraction of local details and improves feature extraction efficiency. In addition, the DAMF-DETR model uses a dual-path attention feature fusion module (DAFF) to capture fine details of densely packed small objects more effectively. We also introduce a novel and efficient multiscale frequency domain pyramid network, termed EMSF-FPN, which employs multiscale feature fusion and frequency domain attention mechanisms to focus on small object details, and maintains high detection accuracy even under low-contrast conditions. Finally, we introduce the Wise-Focaler-MPDIoU (WF-MPDIoU Loss), which dynamically adjusts weights using a scale factor to improve regression accuracy and accelerate convergence. Compared to the baseline model, DAMF-DETR achieves improvements of 4.1%, 3.6%, and 4.2% in the mAP50 metric on the VisDrone2019, NWPU VHR-10, and DOTA-v1.0 remote sensing image datasets, respectively, while reducing the number of parameters by 18.1%. These results demonstrate that DAMF-DETR enhances detection accuracy for small objects while maintaining a lightweight and efficient architecture.