Abstract
Multi-scale object detection in remote sensing imagery poses significant challenges, including substantial variations in object size, diverse orientations, and interference from complex backgrounds. To address these issues, we propose SADFF-Net, a novel detection framework that incorporates a Multi-scale Contextual Attention Fusion (MCAF) module to enhance information exchange between feature layers and suppress irrelevant feature interference. In addition, SADFF-Net employs an Adaptive Spatial Feature Fusion (ASFF) module to improve semantic consistency across feature layers by assigning spatial weights at multiple scales. To enhance adaptability to scale variations, the regression head integrates a deformable convolution. In contrast, the classification head utilizes depth-wise separable convolutions to significantly reduce computational complexity without compromising detection accuracy. Extensive experiments on the DOTAv1 and DIOR_R datasets demonstrate that SADFF-Net outperforms current state-of-the-art methods in multi-scale object detection.
Funding Information
  • Youth Project of the Applied Basic Research Program of Shanxi Province (202203021222027)