Towards Robust Plant Disease Diagnosis with Hard-sample Re-mining Strategy

TL;DR

This paper introduces HSReM, a strategic hard-sample re-mining training method that improves plant disease detection accuracy by effectively selecting challenging healthy and diseased samples, outperforming existing models.

Contribution

The paper proposes a novel hard-sample re-mining strategy (HSReM) that enhances detection performance by strategically selecting training samples, addressing the challenge of similar healthy and diseased plant data.

Findings

HSReM significantly improves diagnostic accuracy on large-scale unseen data.

The model trained with HSReM outperforms state-of-the-art classification and detection models.

HSReM effectively balances healthy and diseased sample training, reducing mis-detections.

Abstract

With rich annotation information, object detection-based automated plant disease diagnosis systems (e.g., YOLO-based systems) often provide advantages over classification-based systems (e.g., EfficientNet-based), such as the ability to detect disease locations and superior classification performance. One drawback of these detection systems is dealing with unannotated healthy data with no real symptoms present. In practice, healthy plant data appear to be very similar to many disease data. Thus, those models often produce mis-detected boxes on healthy images. In addition, labeling new data for detection models is typically time-consuming. Hard-sample mining (HSM) is a common technique for re-training a model by using the mis-detected boxes as new training samples. However, blindly selecting an arbitrary amount of hard-sample for re-training will result in the degradation of diagnostic performance for other diseases due to the high similarity between disease and healthy data. In this paper, we propose a simple but effective training strategy called hard-sample re-mining (HSReM), which is designed to enhance the diagnostic performance of healthy data and simultaneously improve the performance of disease data by strategically selecting hard-sample training images at an appropriate level. Experiments based on two practical in-field eight-class cucumber and ten-class tomato datasets (42.7K and 35.6K images) show that our HSReM training strategy leads to a substantial improvement in the overall diagnostic performance on large-scale unseen data. Specifically, the object detection model trained using the HSReM strategy not only achieved superior results as compared to the classification-based state-of-the-art EfficientNetV2-Large model and the original object detection model, but also outperformed the model using the HSM strategy in multiple evaluation metrics.