Research Article | Open Access

Volume 2024 |Article ID 0208 | https://doi.org/10.34133/plantphenomics.0208

Local and Global Feature-Aware Dual-Branch Networks for Plant Disease Recognition

Jianwu Lin,^1,2,3,4 Xin Zhang ,^1,2,3,4 Yongbin Qin,^1,2 Shengxian Yang,^3,4 Xingtian Wen,³ Tomislav Cernava,⁵ Quirico Migheli,⁶ Xiaoyulong Chen ^4,7

¹Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China
²State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China
³College of Big Data and Information Engineering, Guizhou University, Guiyang 550025, China
⁴Guizhou-Europe Environmental Biotechnology and Agricultural Informatics Oversea Innovation Center in Guizhou University, Guizhou Provincial Science and Technology Department, Guiyang 550025, China
⁵School of Biological Sciences, Faculty of Environmental and Life Sciences, University of Southampton, Southampton S017 1BJ, UK
⁶Dipartimento di Agraria and NRD—Nucleo di Ricerca sulla Desertificazione, Università degli Studi di Sassari, Sassari, Italy
⁷College of Life Sciences, Guizhou University, Guiyang 550025, China

Abstract

Accurate identification of plant diseases is important for ensuring the safety of agricultural production. Convolutional neural networks (CNNs) and visual transformers (VTs) can extract effective representations of images and have been widely used for the intelligent recognition of plant disease images. However, CNNs have excellent local perception with poor global perception, and VTs have excellent global perception with poor local perception. This makes it difficult to further improve the performance of both CNNs and VTs on plant disease recognition tasks. In this paper, we propose a local and global feature-aware dual-branch network, named LGNet, for the identification of plant diseases. More specifically, we first design a dual-branch structure based on CNNs and VTs to extract the local and global features. Then, an adaptive feature fusion (AFF) module is designed to fuse the local and global features, thus driving the model to dynamically perceive the weights of different features. Finally, we design a hierarchical mixed-scale unit-guided feature fusion (HMUFF) module to mine the key information in the features at different levels and fuse the differentiated information among them, thereby enhancing the model's multiscale perception capability. Subsequently, extensive experiments were conducted on the AI Challenger 2018 dataset and the self-collected corn disease (SCD) dataset. The experimental results demonstrate that our proposed LGNet achieves state-of-the-art recognition performance on both the AI Challenger 2018 dataset and the SCD dataset, with accuracies of 88.74% and 99.08%, respectively.