ce Foundation Project (No. 2024MS06002), the Inner Mongolia Autonomous Region universities innovative research team project (No. NMGIRT2313) and the Inner Mongolia Natural Science Foundation Project (No. 2025ZD012). Data availability statement Publicly available datasets were analyzed in this study. This data can be found here: https://www.kaggle.com/competitions/plant-pathology-2021-fgvc8 ; https://github.com/JasonYangCode/AppleLeaf9 ; https://www.scidb.cn/en/detail?dataSetId=0e1f57004db842f99668d82183afd578 . Author contributions YJ: Data curation, Formal analysis, Investigation, Methodology, Software, Validation, Visualization, Writing – original draft. HL: Funding acquisition, Resources,
Open resource ↗plant-pathology-2021-fgvc8 · plant-pathology-2021-fgvc8 · lines:727-753Unverified paper record
LCAMNet: a lightweight model for apple leaf disease classification in natural environments.
Frontiers in plant science · 12 Aug 2025 · 10.3389/fpls.2025.1626569
Abstract
Apple leaf diseases severely affect the quality and yield of apples, and accurate classification is crucial for reducing losses. However, in natural environments, the similarity between backgrounds and lesion areas makes it difficult for existing models to balance lightweight design and high accuracy, limiting their practical applications. In order to resolve the aforementioned problem, this paper introduces a lightweight converged attention multi-branch network named LCAMNet. The network integrates depthwise separable convolutions and structural re-parameterization techniques to achieve efficient modeling. To avoid feature loss caused by single downsampling operations, a dual-branch downsampling module is designed. A multi-scale structure is introduced to enhance lesion feature diversity representation. An improved triplet attention mechanism is utilized to better capture deep lesion features. Furthermore, a dataset named SCEBD is constructed, containing multiple common disease types and interference factors under natural environments, realistically reflecting orchard conditions. Experimental results show that LCAMNet achieves 92.60% accuracy on the SCEBD and 95.31% on a public dataset, with only 0.03 GFLOPs and 1.30M parameters. The model maintains high accuracy while remaining lightweight, enabling effective apple leaf disease classification in natural environments on devices with limited resources.
Plant phenotyping relevance
リンゴ葉の病徴を画像から分類する軽量モデルを開発し、自然環境データセットを構築・評価しており、植物病害状態の画像ベース表現型推定が中心である。
abstractthis paper introduces a lightweight converged attention multi-branch network named LCAMNet.
abstractFurthermore, a dataset named SCEBD is constructed, containing multiple common disease types and interference factors under natural environments
abstractExperimental results show that LCAMNet achieves 92.60% accuracy on the SCEBD and 95.31% on a public dataset
Code and data availability
The paper's data availability statement links three public image datasets directly used in its experiments: the FGVC8 Plant Pathology 2021 Kaggle dataset, the AppleLeaf9 GitHub dataset, and the ATLDSD dataset on ScienceDB. No author analysis code or trained model is released, and the self-constructed SCEBD has no own公开
omous Region universities innovative research team project (No. NMGIRT2313) and the Inner Mongolia Natural Science Foundation Project (No. 2025ZD012). Data availability statement Publicly available datasets were analyzed in this study. This data can be found here: https://www.kaggle.com/competitions/plant-pathology-2021-fgvc8 ; https://github.com/JasonYangCode/AppleLeaf9 ; https://www.scidb.cn/en/detail?dataSetId=0e1f57004db842f99668d82183afd578 . Author contributions YJ: Data curation, Formal analysis, Investigation, Methodology, Software, Validation, Visualization, Writing – original draft. HL: Funding acquisition, Resources, Writing – review & editing. XF: Project administration, Supervis
Open resource ↗JasonYangCode/AppleLeaf9 · JasonYangCode/AppleLeaf9 · lines:727-753team project (No. NMGIRT2313) and the Inner Mongolia Natural Science Foundation Project (No. 2025ZD012). Data availability statement Publicly available datasets were analyzed in this study. This data can be found here: https://www.kaggle.com/competitions/plant-pathology-2021-fgvc8 ; https://github.com/JasonYangCode/AppleLeaf9 ; https://www.scidb.cn/en/detail?dataSetId=0e1f57004db842f99668d82183afd578 . Author contributions YJ: Data curation, Formal analysis, Investigation, Methodology, Software, Validation, Visualization, Writing – original draft. HL: Funding acquisition, Resources, Writing – review & editing. XF: Project administration, Supervision, Writing – review & editing. BW: Project a
Open resource ↗0e1f57004db842f99668d82183afd578 · lines:727-753This is an automatically classified, unverified record. Curator approval is required before any resource enters the Catalog.