通过知识蒸馏改进轻量级杂草检测
Improving Lightweight Weed Detection via Knowledge Distillation
AI总结：
本研究提出利用CWD和MGD知识蒸馏技术，以YOLO11x为教师模型提升YOLO11n轻量级杂草检测模型的性能，在甜菜与杂草数据集上mAP50提升达2.5%和1.9%，并在Jetson和树莓派设备上验证了实时部署可行性。
摘要：
杂草检测是精准农业的关键组成部分，有助于实现定向喷洒除草剂并减少环境影响。然而，在资源有限的平台上部署准确的目标检测模型仍然具有挑战性，特别是在区分植物表型应用中常见的视觉相似的杂草物种时。在本研究中，我们研究了通道式知识蒸馏（CWD）和掩码生成蒸馏（MGD），以提升用于实时智能喷洒系统的轻量级模型的性能。利用YOLO11x作为教师模型，YOLO11n同时作为参考模型和学生模型，CWD和MGD均有效地将知识从教师模型转移给学生模型。我们的实验在包含甜菜作物和四种杂草类型（Cirsium、Convolvulus、Fallopia和Echinochloa）的真实数据集上进行，结果显示所有类别的AP50均持续提升。蒸馏后的CWD学生模型实现了2.5%的显著提升，MGD实现了1.9%的mAP50提升，且未增加模型复杂度。此外，我们通过在Jetson Orin Nano和Raspberry Pi 5嵌入式设备上评估学生YOLO11n模型，验证了实时部署的可行性，并进行了五次独立运行以评估随机种子下的性能稳定性。这些发现证实CWD和MGD是提升精准农业和植物表型场景中基于深度学习的杂草检测准确性的有效、高效且实用的方法。
英文摘要：
Weed detection is a critical component of precision agriculture, facilitating targeted herbicide application and reducing environmental impact. However, deploying accurate object detection models on resource-limited platforms remains challenging, particularly when differentiating visually similar weed species commonly encountered in plant phenotyping applications. In this work, we investigate Channel-wise Knowledge Distillation (CWD) and Masked Generative Distillation (MGD) to enhance the performance of lightweight models for real-time smart spraying systems. Utilizing YOLO11x as the teacher model and YOLO11n as both reference and student, both CWD and MGD effectively transfer knowledge from the teacher to the student model. Our experiments, conducted on a real-world dataset comprising sugar beet crops and four weed types (Cirsium, Convolvulus, Fallopia, and Echinochloa), consistently show increased AP50 across all classes. The distilled CWD student model achieves a notable improvement of 2.5% and MGD achieves 1.9% in mAP50 over the baseline without increasing model complexity. Additionally, we validate real-time deployment feasibility by evaluating the student YOLO11n model on Jetson Orin Nano and Raspberry Pi 5 embedded devices, performing five independent runs to evaluate performance stability across random seeds. These findings confirm CWD and MGD as an effective, efficient, and practical approach for improving deep learning-based weed detection accuracy in precision agriculture and plant phenotyping scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
