Li Yang, Chao Xuewei
College of Mechanical and Electrical Engineering, Shihezi University, Xinjiang, China.
School of Electrical and Information Engineering, Tianjin University, Tianjin, China.
Plant Methods. 2021 Jun 27;17(1):68. doi: 10.1186/s13007-021-00770-1.
Learning from a few samples to automatically recognize the plant leaf diseases is an attractive and promising study to protect the agricultural yield and quality. The existing few-shot classification studies in agriculture are mainly based on supervised learning schemes, ignoring unlabeled data's helpful information.
In this paper, we proposed a semi-supervised few-shot learning approach to solve the plant leaf diseases recognition. Specifically, the public PlantVillage dataset is used and split into the source domain and target domain. Extensive comparison experiments considering the domain split and few-shot parameters (N-way, k-shot) were carried out to validate the correctness and generalization of proposed semi-supervised few-shot methods. In terms of selecting pseudo-labeled samples in the semi-supervised process, we adopted the confidence interval to determine the number of unlabeled samples for pseudo-labelling adaptively.
The average improvement by the single semi-supervised method is 2.8%, and that by the iterative semi-supervised method is 4.6%.
The proposed methods can outperform other related works with fewer labeled training data.
从少量样本中学习以自动识别植物叶片病害是一项旨在保护农业产量和质量的具有吸引力且前景广阔的研究。农业领域现有的少样本分类研究主要基于监督学习方案，忽略了未标记数据的有用信息。
本文提出了一种半监督少样本学习方法来解决植物叶片病害识别问题。具体而言，使用公开的植物村数据集并将其划分为源域和目标域。进行了考虑域划分和少样本参数（N 路，k 次）的广泛比较实验，以验证所提出的半监督少样本方法的正确性和泛化性。在半监督过程中选择伪标记样本时，我们采用置信区间来自适应地确定用于伪标记的未标记样本数量。
单一半监督方法的平均改进率为 2.8%，迭代半监督方法的平均改进率为 4.6%。
所提出的方法在标记训练数据较少的情况下能够优于其他相关工作。
Zotero 插件
