Lesion Detection on Leaves using Class Activation Maps

TL;DR

This paper introduces a novel lesion detection method on plant leaves using class activation maps from a ResNet-18 classifier, effectively identifying lesions without requiring detailed annotations.

Contribution

The study presents a new approach leveraging CAMs from ResNet-18 for lesion detection, avoiding the need for lesion-specific annotations during training.

Findings

Achieved a 0.45 success rate in lesion location prediction.

Utilized CAMs to detect small lesions effectively.

Eliminated the need for lesion annotation in training.

Abstract

Lesion detection on plant leaves is a critical task in plant pathology and agricultural research. Identifying lesions enables assessing the severity of plant diseases and making informed decisions regarding disease control measures and treatment strategies. To detect lesions, there are studies that propose well-known object detectors. However, training object detectors to detect small objects such as lesions can be problematic. In this study, we propose a method for lesion detection on plant leaves utilizing class activation maps generated by a ResNet-18 classifier. In the test set, we achieved a 0.45 success rate in predicting the locations of lesions in leaves. Our study presents a novel approach for lesion detection on plant leaves by utilizing CAMs generated by a ResNet classifier while eliminating the need for a lesion annotation process.