知识蒸促进了轻量级和高效的植物疾病检测模型
Qianding Huang1, Xingcai Wu1, Qi Wang1,2
1State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China.
Plant phenomics (Washington, D.C.)
|July 3, 2023
概括
这项研究引入了一种用于检测植物疾病的新型知识蒸方法,创建轻量级的人工智能模型,用于在移动设备上诊断多种作物疾病. 该技术在较少的参数下实现高精度,增强智能农业应用.
科学领域:
- 农业技术 农业技术
- 计算机视觉 计算机视觉 计算机视觉
- 人工智能的人工智能是人工智能.
背景情况:
- 及时诊断植物疾病对于防止作物损失和确保粮食安全至关重要.
- 目前用于植物疾病的物体检测方法是准确的,但仅限于单一作物,通常需要大量的计算资源.
- 在移动农业设备上部署疾病诊断模型是具有挑战性的,因为模型大小和参数数量,通常导致模型被压缩时的精度降低.
研究的目的:
- 开发一种轻量级和高效的植物疾病检测方法,用于诊断各种作物的多种疾病.
- 解决现有模型在单一作物特异性和可部署在移动农业设备上的局限性.
- 为了保持高的诊断准确度,同时显著减少模型参数.
主要方法:
- 提出了一种利用多阶段知识蒸的植物疾病检测方法.
- 使用两种不同的策略设计了四种轻量级学生模型 (YOLOR-Light-v1,YOLOR-Light-v2,移动YOLOR-v1,移动YOLOR-v2).
- 采用YOLOR模型作为知识蒸的教师模型.
主要成果:
- 在显著减少模型参数的PlantDoc数据集上实现了60.4%的mAP@0.5.
- 提出的多阶段知识蒸方法提高了轻型模型的性能.
- 在多种作物,多种疾病诊断的准确性和效率方面,超越了现有的方法.
结论:
- 多阶段知识蒸有效地创建轻量级但准确的植物疾病检测模型.
- 开发的技术适用于农业移动设备的部署,支持智能农业.
- 该方法表明有可能扩展到其他计算机视觉任务,如图像分类和细分.
相关概念视频
02:16Light Acquisition
8.5K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
8.5K
02:35Key Elements for Plant Nutrition
18.8K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
18.8K