基于小样本学习的植物病害识别研究*

为在仅有少量训练样本条件下获得较高的植物病害分类精度,采用小样本学习模型作为病害分类器,在匹配网络、原型网络和关系网络3种典型小样本学习算法框架下分别采用Conv4、Conv6、ResNet10、ResNet18和ResNet34 5种浅层网络作为特征提取网络,在PlantVillage植物病害数据集上对病害识别性能进行对比试验。在1shot条件下,匹配网络、原型网络和关系网络对植物叶片病害识别的平均准确率分别为72.29%、72.43%和69.45%;其中原型网络+ResNet34为表现最好的组合,病害识别准确率达到了77.60%。在5shot条件下,匹配网络、原型网络和关系网络平均准确率分别为87.11%、87.50%和82.92%,各种网络病害识别准确率比1shot条件均有明显提升;原型网络+ResNet34依旧是表现最佳的组合方式,识别准确率达到89.66%。上述试验结果表明,通过优选小样本学习框架和特征提取网络的组合方式,对于少量样本的病害也能取得较好的识别效果。

Research on plant disease identification based on few-shot learning

In order to obtain high accuracy of plant disease classification with only a few training samples, a few-shot learning model was used as the disease classifier, and five kinds of shallow networks, Conv4, Conv6, ResNet10, ResNet18, and ResNet34, were used as feature extraction networks under the framework of three typical few-shot learning algorithms, including MatchingNet, ProtoNet, and RelationNet. Their performances were compared on the plant disease data set of PlantVillage. Under the condition of 5way、1shot, the average accuracies of MatchingNet, ProtoNet, and RelationNet were 72.29%, 72.43%, and 69.45%, respectively. ProtoNet+ResNet34 was the optimal combinational mode, and the accuracy reached 77.60%. Under the condition of 5way、5shot, the average accuracies of MatchingNet, ProtoNet, and RelationNet were 87.11%, 87.50%, and 82.92%, respectively. The accuracies were significantly improved compared to that of the 1shot condition. ProtoNet+ResNet34 was still the optimal one with an accuracy of 89.66%. The above test results show that by optimizing the combination of a few-shot learning framework and feature extraction network, the recognition model can achieve good effects for diseases with a small number of samples.