Double Attention-based Lightweight Network for Plant Pest Recognition

TL;DR

This paper introduces a novel double attention-based lightweight deep learning model for plant pest recognition, achieving high accuracy with faster training on small datasets, outperforming existing methods.

Contribution

A new lightweight network with double attention mechanism is proposed, improving pest classification accuracy and efficiency, especially on small datasets.

Findings

Achieved over 96% accuracy on large datasets

Outperformed existing methods on multiple datasets

Effective on small sample sizes

Abstract

Timely recognition of plant pests from field images is significant to avoid potential losses of crop yields. Traditional convolutional neural network-based deep learning models demand high computational capability and require large labelled samples for each pest type for training. On the other hand, the existing lightweight network-based approaches suffer in correctly classifying the pests because of common characteristics and high similarity between multiple plant pests. In this work, a novel double attention-based lightweight deep learning architecture is proposed to automatically recognize different plant pests. The lightweight network facilitates faster and small data training while the double attention module increases performance by focusing on the most pertinent information. The proposed approach achieves 96.61%, 99.08% and 91.60% on three variants of two publicly available datasets with 5869, 545 and 500 samples, respectively. Moreover, the comparison results reveal that the proposed approach outperforms existing approaches on both small and large datasets consistently.