AUTHOR=Xu Laixiang , Song Hongyun , Yang Xiaodong , Xu Peng , Cai Zhaopeng 

TITLE=ViTKAB: an efficient deep learning network for cotton leaf disease identification

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 16 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2025.1719877

DOI=10.3389/fpls.2025.1719877

ISSN=1664-462X

ABSTRACT=IntroductionCotton is a vital global economic crop and textile material, yet its yield and quality are threatened by leaf diseases such as brown spot, verticillium wilt, wheel spot, and fusarium wilt.MethodsWe propose ViTKAB, a cotton disease recognition model based on an enhanced Vision Transformer that integrates a Kolmogorov-Arnold network and a BiFormer module. The model optimizes the Vision Transformer architecture to improve inference speed, employs nonlinear feature representation to better capture complex disease characteristics, and incorporates sparse dynamic attention to enhance robustness and accuracy.ResultsExperiments show that ViTKAB achieves an average recognition accuracy of 98.05% across four cotton leaf diseases, outperforming models such as CoAtNet-7, CLIP, and PaLI.ConclusionsThis method offers valuable insights for advancing intelligent crop disease detection systems and exhibits strong potential for deployment on edge devices.