EUVIMEDSkopri EUVIMED
Crossref

Lightweight crop disease identification network based on frequency domain and channel mixing attention and cross‐scale semantic fusion

Tiancan Jian, Haixia Qi iD, Riyao Chen, Yu Liang, Guangsheng Liang, Xiwen Luo

Pest Management Science · 2025-12 · 81 (12) · 8643-8660

DOI: 10.1002/ps.70170 ↗

At a glance

Journal article in Pest Management Science, published online on 2025-09-24. Written by Tiancan Jian and 5 co-authors. Institution: College of Engineering, South China Agricultural University, Guangzhou, China. Major MEDLINE topics: Plant Diseases, Crops, Agricultural. Cited 4 times so far (Crossref); 19 references. Funded by: Xiwen Luo, Haixia Qi, South China Agri-cultural University.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

BACKGROUND Accurate identification of crop diseases is essential for enhancing agricultural productivity; however, it encounters challenges arising from complex field conditions and the constraints of deploying on resource‐limited devices. This study aims to develop a lightweight yet accurate framework, referred to as FCDRNet, which integrates feature enhancement and compression techniques to facilitate practical deployment in the field. RESULTS FCDRNet introduces three key innovations: 1) a frequency‐channel mixing attention (FCMA) module that integrates median‐enhanced channel pooling with wavelet‐based frequency attention to effectively capture both local and global features; 2) a cross‐scale semantic fusion (CSF) module that facilitates adaptive multiscale lesion recognition; and 3) a DepGraph‐RKD compression strategy that reduces parameters by 70.6% (from 4.32 M to 1.27 M) and FLOPs by 56.98% (from 256.73 M to 110.43 M). Evaluations on the Peanut Leaf Disease Dataset (PLDD) and PlantVillage Dataset (PD) datasets demonstrate that FCDRNet achieves accuracies of 96.60% and 99.67%, respectively, surpassing baseline models by 3.31% and 2.23%. Notably, the compression method maintains robustness with an accuracy degradation of ≤0.14%, enabling real‐time inference at 14.84 ms on embedded devices. CONCLUSION FCDRNet offers scalable solutions for smart agriculture by synergistically integrating attention mechanisms, semantic fusion and dependency‐aware compression. It achieves a balanced performance in terms of accuracy and efficiency, with accuracy rates of 96.60%, 99.67% and 97.77% on three datasets: the PLDD, PD and PlantDoc, respectively. This performance has propelled the development of practical, field‐deployable crop disease monitoring systems, effectively addressing critical gaps in identification accuracy and the limitations associated with edge deployment. © 2025 Society of Chemical Industry.

Subjects

MeSH terms (MEDLINE)

Plant DiseasesCrops, AgriculturalSemanticsArachis

Author keywords

DepGraph pruning‐RKD distillationcross‐scale semantic fusionfrequency domain and channel mixing attentionlightweight crop disease identification

Authors and institutions

  • College of Engineering, South China Agricultural University, Guangzhou, China.
  • Guangdong Laboratory for Lingnan Modern Agriculture, Guangzhou, China.
  • School of Automation Science and Engineering, South China University of Technology, Guangzhou, China.
  • Key Laboratory of Key Technology on Agricultural Machine and Equipment (South China Agricultural University), Ministry of Education, Guangzhou, China.

ORCID profiles: Haixia Qi

Funding

  • Xiwen Luo
  • Haixia Qi
  • South China Agri-cultural University
  • National Key Research and Development Subproject, which is a national key research and development project of South China Agricultural University

Cite

APA

Jian, T., Qi, H., Chen, R., Liang, Y., Liang, G., & Luo, X. (2025). Lightweight crop disease identification network based on frequency domain and channel mixing attention and cross‐scale semantic fusion. Pest Management Science, 81(12), 8643-8660. https://doi.org/10.1002/ps.70170

Vancouver

Jian T, Qi H, Chen R, Liang Y, Liang G, Luo X. Lightweight crop disease identification network based on frequency domain and channel mixing attention and cross‐scale semantic fusion. Pest Management Science. 2025;81(12):8643-8660. doi:10.1002/ps.70170

BibTeX
@article{Jian2025,
  author = {Jian, Tiancan and Qi, Haixia and Chen, Riyao and Liang, Yu and Liang, Guangsheng and Luo, Xiwen},
  title = {Lightweight crop disease identification network based on frequency domain and channel mixing attention and cross‐scale semantic fusion},
  journal = {Pest Management Science},
  year = {2025},
  volume = {81},
  number = {12},
  pages = {8643--8660},
  doi = {10.1002/ps.70170}
}
Start for free →