Ziyu Fan

MD-YOLO: An Improved YOLO26-Based Model for Small-Object Detection in UAV Aerial Imagery

MD-YOLO is proposed, an improved object detection model tailored for UAV scenarios, built upon the YOLO26 baseline, that incorporates three lightweight modules—IMO, DS-SPPF, and HPConv to optimize backbone feature extraction, multi-scale contextual aggregation, and Neck downsampling, thereby enhancing the model’s detec...