Rectified Meta-Learning from Noisy Labels for Robust Image-based Plant Disease Diagnosis
This addresses the challenge of label noise in agricultural AI applications, offering a plug-and-play solution for robust disease diagnosis, though it is incremental as it builds on existing meta-learning and CNN methods.
The paper tackles the problem of noisy labels in CNN-based plant disease diagnosis from leaf images by proposing a rectified meta-learning module that trains a noise-robust network without extra supervision, resulting in accelerated convergence and improved classification accuracy.
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.