A Wireless Collaborated Inference Acceleration Framework for Plant Disease Recognition

TL;DR

This paper introduces a collaborative inference framework combining edge devices and cloud servers, using deep reinforcement learning for pruning and optimal split point selection, to accelerate plant disease recognition with high accuracy and low energy consumption.

Contribution

It presents a novel collaborative inference system with reinforcement learning-based model pruning and split point optimization for efficient plant disease recognition.

Findings

Significantly increased inference speed.

Maintained acceptable recognition accuracy.

Reduced energy consumption during inference.

Abstract

Plant disease is a critical factor affecting agricultural production. Traditional manual recognition methods face significant drawbacks, including low accuracy, high costs, and inefficiency. Deep learning techniques have demonstrated significant benefits in identifying plant diseases, but they still face challenges such as inference delays and high energy consumption. Deep learning algorithms are difficult to run on resource-limited embedded devices. Offloading these models to cloud servers is confronted with the restriction of communication bandwidth, and all of these factors will influence the inference's efficiency. We propose a collaborative inference framework for recognizing plant diseases between edge devices and cloud servers to enhance inference speed. The DNN model for plant disease recognition is pruned through deep reinforcement learning to improve the inference speed and reduce energy consumption. Then the optimal split point is determined by a greedy strategy to achieve the best collaborated inference acceleration. Finally, the system for collaborative inference acceleration in plant disease recognition has been implemented using Gradio to facilitate friendly human-machine interaction. Experiments indicate that the proposed collaborative inference framework significantly increases inference speed while maintaining acceptable recognition accuracy, offering a novel solution for rapidly diagnosing and preventing plant diseases.