Abstract
To address false detections in small object detection within remote sensing imagery caused by complex backgrounds and minute target sizes, we propose an enhanced YOLOv8s detection algorithm, named AL-YOLOv8. The detection head is designed based on Adaptive Spatial Feature Fusion (ASFF) to resolve issues where shallow-level detail features of small remote sensing targets are easily disrupted by backgrounds, while deep-level semantic features lack sufficient representation. We embed Large-Kernel Separate Attention (LSKA) in the deep feature layer to expand the receptive field and enhance the response intensity of small target features. Additionally, an IFIoU loss function is introduced by combining the dynamic attention mechanism from FocalerIoU with InnerIoU, mitigating regression bias for small target bounding boxes and improving small target localization accuracy. On the DIOR, RSOD, and NWPU VHR-10 datasets, the AL-YOLOv8 model achieves precision rates of 91.5%, 94.2%, and 91.8%, respectively, with mAP@0.5 scores of 89.8%, 96.9%, and 92.2%. These results demonstrate consistent improvements over YOLOv8s and show that AL-YOLOv8 effectively reduces false detections and enhances detection accuracy for small object detection in remote sensing applications.