An Improved YOLOv8n Based Marine Debris Recognition Algorithm

This work proposes S<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>-YOLO, a lightweight marine-debris detector that integrates a parameter-free space-to-depth down-sampling block and a grouped-shuffle Slim-Neck. Compared with YOLOv8n on the TrashCan-Instance benchmark, S<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>-YOLO cuts GFLOPs by 14.8 % and boosts mAP50-95 by 2.8 %, providing a compact yet accurate solution for embedded cleanup robots.