A lightweight and generalizable deep learning framework for early detection of rice leaf diseases in complex field environments
Chong Zhang, Xiaoxi Hao, Jianan Liang, Lili Li, Wenwei Li · 2025
Read A lightweight and generalizable deep learning framework for early detection of rice leaf diseases in complex field environments by Chong Zhang, Xiaoxi Hao, Jianan Liang, Lili Li, Wenwei Li (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12749937.txt.
Description
Chong Zhang and co-authors built this 2025 lightweight AI for catching rice leaf disease early in messy real fields. Early lesions are faint, light shifts, leaves overlap, and farm devices are weak, so heavy models fail twice over. Their framework stacks three slim modules: one widens the view for subtle spots, one mixes attention across scales, and one trims the detection head with grouped math.
On a dedicated rice data set, the system scored about sixty-three percent on a strict accuracy measure, beating rivals while staying small. The design also aims to travel across disease types and plant species. Early, cheap detection on a phone-class device could let farmers treat small patches before whole fields sicken, guarding a staple crop.
Catalog record
| CREATOR | Chong Zhang, Xiaoxi Hao, Jianan Liang, Lili Li, Wenwei Li |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 277 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |