Deep learning plays an important role in modern agriculture, especially in
plant pathology using leaf images where convolutional neural networks (CNN) are
attracting a lot of attention. While numerous reviews have explored the
applications of deep learning within this research domain, there remains a
notable absence of an empirical study to offer insightful comparisons due to
the employment of varied datasets in the evaluation. Furthermore, a majority of
these approaches tend to address the problem as a singular prediction task,
overlooking the multifaceted nature of predicting various aspects of plant
species and disease types. Lastly, there is an evident need for a more profound
consideration of the semantic relationships that underlie plant species and
disease types. In this paper, we start our study by surveying current deep
learning approaches for plant identification and disease classification. We
categorise the approaches into multi-model, multi-label, multi-output, and
multi-task, in which different backbone CNNs can be employed. Furthermore,
based on the survey of existing approaches in plant pathology and the study of
available approaches in machine learning, we propose a new model named
Generalised Stacking Multi-output CNN (GSMo-CNN). To investigate the
effectiveness of different backbone CNNs and learning approaches, we conduct an
intensive experiment on three benchmark datasets Plant Village, Plant Leaves,
and PlantDoc. The experimental results demonstrate that InceptionV3 can be a
good choice for a backbone CNN as its performance is better than AlexNet,
VGG16, ResNet101, EfficientNet, MobileNet, and a custom CNN developed by us.
Interestingly, empirical results support the hypothesis that using a single
model can be comparable or better than using two models. Finally, we show that
the proposed GSMo-CNN achieves state-of-the-art performance on three benchmark
datasets.

通过对植物病理学方面的当前深度学习方法进行调研和现有机器学习方法的研究，我们提出了一种名为通用堆叠多输出 CNN 的新模型（GSMo-CNN），并在三个基准数据集上进行了大量实验。实验结果表明，InceptionV3 是作为骨干 CNN 的较好选择，其性能优于 AlexNet、VGG16、ResNet101、EfficientNet、MobileNet 和我们开发的自定义 CNN，并证实单一模型的使用可以与或优于使用两个模型。最终，我们展示了提出的 GSMo-CNN 在三个基准数据集上达到了最先进的性能。

深度学习在叶片图像中植物识别和病害分类的应用：多预测方法

Deep Learning for Plant Identification and Disease Classification from  Leaf Images: Multi-prediction Approaches

Lesion detection on plant leaves is a critical task in plant pathology and
agricultural research. Identifying lesions enables assessing the severity of
plant diseases and making informed decisions regarding disease control measures
and treatment strategies. To detect lesions, there are studies that propose
well-known object detectors. However, training object detectors to detect small
objects such as lesions can be problematic. In this study, we propose a method
for lesion detection on plant leaves utilizing class activation maps generated
by a ResNet-18 classifier. In the test set, we achieved a 0.45 success rate in
predicting the locations of lesions in leaves. Our study presents a novel
approach for lesion detection on plant leaves by utilizing CAMs generated by a
ResNet classifier while eliminating the need for a lesion annotation process.

本研究提出了一种基于 ResNet-18 分类器生成类激活映射进行的植物叶片病斑检测方法，无需进行病斑注释，可以有效解决小目标检测问题，从而实现对植物病害的有效控制，成功率为 0.45。