A Lightweight Improved YOLO11 for Small-Object Detection in UAV Imagery

Abstract

Small-object detection in unmanned aerial vehicle (UAV) imagery remains challenging due to small target scales, dense target distributions, complex backgrounds, and limited onboard computational resources. To address these coupled problems, this paper proposes ASE-YOLO11, a lightweight improved detector based on YOLO11n for UAV small-object detection. ASE denotes Aerial Small-object Enhancement, indicating that the method is designed for aerial scenes dominated by small targets. The proposed method combines a P2 small-object detection branch, a Normalized Wasserstein Distance (NWD)-based localization loss, and a lightweight task-aligned detection head. These components respectively improve high-resolution feature representation, stabilize tiny-box regression, and align classification and localization cues on shallow feature maps. Experiments on VisDrone2019-DET show that ASE-YOLO11 improves mAP50 from 0.320 to 0.337 and recall from 0.344 to 0.360 compared with YOLO11n, while maintaining a compact model size of 2.665 M parameters.