野生植物病的分类使用视觉变换器和专家混合物
Zafar Salman1, Abdullah Muhammad1, Dongil Han1
1Department of Computer Science and Engineering, Sejong University, Seoul, Republic of Korea.
Frontiers in plant science
|July 3, 2025
概括
这项研究引入了一种新的深度学习模型,将视觉转换器与植物疾病分类专家组合相结合. 该方法在现实世界农业环境中显著提高了准确性,克服了各种图像条件的挑战.
科学领域:
- 计算机视觉 计算机视觉
- 植物病理学 植物病理学
- 机器学习 机器学习
背景情况:
- 植物疾病分类的深度学习模型在高质量的图像中表现出色,但由于照明,捕获条件和疾病严重程度的变化,在现实世界农业环境中扎.
- 这种绩效差距阻碍了人工智能在农业中的实际部署.
研究的目的:
- 开发一个强大的深度学习模型,在多样化,现实世界农业条件下准确地分类植物疾病.
- 解决当前模型对野生图像变异的概括方面的局限性.
主要方法:
- 这是一种新的方法,将视觉变压器 (ViT) 骨干与专家混合 (MoE) 架构相结合.
- 实施基于输入数据特征的动态专家分配门禁机制.
- 结合和直角规则化来增强模型的稳定性和通用性.
主要成果:
- 拟议的MoE-ViT模型比标准ViT实现了20%的准确性改进.
- 在跨域数据集 (从PlantVillage到PlantDoc) 上显示了68%的准确性,表现优于InceptionV3和EfficientNet.
- 在各种数据集中显著提高性能,具有各种图像捕捉条件和疾病严重程度.
结论:
- 专家组合开发的视觉变压器模型为在动态农业环境中可靠识别植物疾病提供了有前途的解决方案.
- 该方法增强了模型的适应性和通用性,为精准农业中有效的AI部署铺平了道路.
相关概念视频
01:28Methods of Classification and Identification
215
Bacterial identification relies on a diverse array of techniques to classify and understand microorganisms, each tailored to uncover specific characteristics. Traditional morphological approaches, while still valuable, are limited for closely related or structurally simple organisms. Modern methods integrate biochemical, serological, genetic, and advanced molecular tools to achieve greater accuracy.Morphological and Biochemical TechniquesMorphological characteristics, such as cell shape and...
215
02:16Light Acquisition
8.6K
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.
8.6K
02:22Introduction to Plant Diversity
45.9K
From Water to Land
45.9K