Plant diseases serve as one of main threats to food security and crop production. It is thus valuable to exploit recent advances of artificial intelligence to assist plant disease diagnosis. One popular approach is to transform this problem as a leaf image classification task, which can be then addressed by the powerful convolutional neural networks (CNNs). However, the performance of CNN-based classification approach depends on a large amount of high-quality manually labeled training data, which are inevitably introduced noise on labels in practice, leading to model overfitting and performance degradation. To overcome this problem, we propose a novel framework that incorporates rectified meta-learning module into common CNN paradigm to train a noise-robust deep network without using extra supervision information. The proposed method enjoys the following merits: i) A rectified meta-learning is designed to pay more attention to unbiased samples, leading to accelerated convergence and improved classification accuracy. ii) Our method is free on assumption of label noise distribution, which works well on various kinds of noise. iii) Our method serves as a plug-and-play module, which can be embedded into any deep models optimized by gradient descent based method. Extensive experiments are conducted to demonstrate the superior performance of our algorithm over the state-of-the-arts.

中文翻译：

---

用于稳健的基于图像的植物病害诊断的噪声标签的修正元学习

植物病害是粮食安全和作物生产的主要威胁之一。因此，利用人工智能的最新进展来辅助植物病害诊断是很有价值的。一种流行的方法是将此问题转换为叶图像分类任务，然后可以通过强大的卷积神经网络 (CNN) 解决该问题。然而，基于CNN的分类方法的性能依赖于大量高质量的人工标记训练数据，在实践中不可避免地会在标签上引入噪声，导致模型过拟合和性能下降。为了克服这个问题，我们提出了一种新颖的框架，该框架将修正的元学习模块合并到常见的 CNN 范式中，以在不使用额外监督信息的情况下训练抗噪深度网络。所提出的方法具有以下优点：i）经过修正的元学习旨在更加关注无偏样本，从而加快收敛速度​​并提高分类精度。ii）我们的方法在假设标签噪声分布的情况下是免费的，它适用于各种噪声。iii) 我们的方法作为即插即用模块，可以嵌入到任何通过基于梯度下降的方法优化的深度模型中。进行了大量实验以证明我们的算法优于最先进的算法。iii) 我们的方法作为即插即用模块，可以嵌入到任何通过基于梯度下降的方法优化的深度模型中。进行了大量实验以证明我们的算法优于最先进的算法。iii) 我们的方法作为即插即用模块，可以嵌入到任何通过基于梯度下降的方法优化的深度模型中。进行了大量实验以证明我们的算法优于最先进的算法。