对比三代YOLO在果园细粒度小目标检测中的表现，找到高效实用的模型配置。
Cross-Generation Optimization of YOLOv26, YOLOv11, and YOLOv8 for Fine-Grained Small-Object Detection and Instance Segmentation in Complex Orchards
- 跨代比较YOLOv8/v11/v26，测试不同规模与960分辨率训练效果
- YOLOv11s-960达最高精度（掩码mAP@50:95=0.402），YOLOv26s-960仅用10.37M参数接近
- 适用于农业机器人感知，尤其适合资源受限场景的小目标分割
果园环境中，因绿叶遮挡、同类相似及果实细节像素不足，细粒度小目标检测与实例分割仍具挑战。本研究针对苹果幼果、花萼和果梗结构，对Ultralytics YOLOv8、YOLOv11和YOLOv26进行跨代基准评估。在常规640×640与聚焦小目标的960×960两种训练配置下，测试五种模型尺度（n, s, m, l, x），共30组实验。模型容量提升并未一致带来精度提高。YOLOv11s-960取得最高掩码mAP@50:95为0.402，框检测mAP@50:95为0.426；而YOLOv26s-960以10.37 M参数和34.1 GFLOPs实现0.397和0.425的相近性能。果梗识别仍是最困难类别。总体而言，紧凑至中等规模的YOLO模型结合小目标优化训练，在精度与效率间取得良好平衡，为农业机器人精细感知提供可行基准。
原文摘要 · Abstract (English)
Small-object detection and instance segmentation remain challenging in orchard environments because of green-on-green similarity, occlusion, and limited pixel representation of fine fruit anatomy. This study presents a cross-generation benchmark of Ultralytics YOLOv8, YOLOv11, and YOLOv26 for detecting and segmenting apple fruitlet, calyx, and peduncle structures for robotic orchard perception. Five model scales (n, s, m, l, and x) were evaluated under conventional 640 x 640 and small-object focused 960 x 960 training configurations, yielding 30 experiments. Increasing model capacity did not consistently improve accuracy. YOLOv11s-960 achieved the highest observed mask mAP@50:95 (0.402) and box mAP@50:95 (0.426), while YOLOv26s-960 achieved comparable values of 0.397 and 0.425 with only 10.37 M parameters and 34.1 GFLOPs. Peduncle remained the most challenging class. Overall, compact-to-moderate YOLO models with small-object-focused training provided favorable accuracy efficiency trade-offs, establishing a practical benchmark for fine-grained agricultural robotics and orchard perception. Github Link: https://github.com/rnjnspkt/Optimizing-and-Comparing-Ultralytics-YOLOv26-YOLOv11-and-YOLOv8-for-Small-Object-Detection-and-Seg
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。