Integrating Kolmogorov-Arnold networks and sparse attention for robust visual plant disease symptom identification across diverse agricultural crops

Abstract

Introduction Accurate and rapid diagnosis of plant leaf disease symptoms is critical for sustainable agricultural crop production, yet traditional methods often lack efficiency and robustness under field conditions. Methods Here, we propose a deep learning framework based on an improved Vision Transformer architecture that integrates a dynamic sparse attention mechanism, termed KBTNet, for targeted feature extraction in symptom-affected regions of leaf images. The model incorporates a learnable nonlinear enhancement module to capture subtle visual disease symptom variations such as lesions, discoloration patterns, and spot distributions, and a lightweight Transformer design to reduce computational cost. Results Evaluated on a multisource dataset containing soybean and tomato leaf images representing diverse disease symptom patterns, our approach achieved 93.19% classification accuracy, outperforming current state-of-the-art models. Additional evaluations on public plant disease datasets from multiple crops further demonstrate the model's ability to recognize disease symptom patterns across diverse crop species. Discussion The proposed framework achieves stable performance across diverse crop and disease symptom categories, maintains high efficiency under reduced parameter complexity, and exhibits strong potential for realtime field diagnostics on edge devices. This work provides a scalable and efficient tool for plant disease symptom detection and classification and supports the integration of visionbased intelligence into crop disease monitoring and management systems.

Plant phenotyping relevance

植物葉画像から病徴（病斑、変色、斑点分布）を抽出・分類する深層学習手法を開発しており、植物病害状態の表現型取得が研究の中心である。

Code and data availability

The paper (KBTNet, a ViT+KAN+sparse-attention plant disease classifier) reports field-collected soybean leaf images and public plant disease datasets, but no authors' public code, dataset, or model deposit URL is provided. The data availability statement only points to the article/Supplementary Material and directs all

No evidence-backed public reproduction asset is currently recorded.