# IRMKD: an application of instance relation matrix in plant disease recognition

## TL;DR

This paper introduces IRMKD, a new method for plant disease recognition that reduces model size and improves speed while maintaining high accuracy.

## Contribution

The novel IRMKD approach uses instance-relation matrices for knowledge distillation, enabling efficient plant disease recognition on low-resource devices.

## Key findings

- The proposed method reduces memory usage and recognition time by an average of 92%.
- Recognition accuracy remains above 93% despite the reduction in model size.
- IRMKD slightly reduces validation accuracy while significantly improving model efficiency.

## Abstract

The recognition and prevention of plant diseases is very important to the growth process. At present, neural networks have achieved good results in plant disease identification, but the development of convolutional neural networks has brought a large number of network parameters and long recognition time, which greatly limits its application on devices that lack computing resources.

To solve this problem, We introduce a novel approach, dubbed instance-relation-matrix based knowledge distillation (IRMKD), that transfers mutual relations of data examples. For concrete realizations of IRMKD, we combine the correlation of the samples with the relationship between the characteristics of the instances and introducing multiple loss functions.

Experimental results show that the proposed method improves educated student models with a significant margin. In particular, for traditional neural networks, our method significantly reduces memory usageand recognition time by an average of 92% and at the same time ensure that the recognition accuracy rate is above 93%, provides a new plant disease recognition method for devices with limited memory and computing resources.

IRMKD can significantly reduce the volume of the model and improve the recognition speed of the model on the premise of slightly reducing the accuracy of the verification set.