A Lightweight Edge-Deployable Framework for Intelligent Rice Disease Monitoring Based on Pruning and Distillation
Wei Liu, Baoquan Duan, Zhipeng Fan, Ming Chen, Zeguo Qiu · 2025
Read A Lightweight Edge-Deployable Framework for Intelligent Rice Disease Monitoring Based on Pruning and Distillation by Wei Liu, Baoquan Duan, Zhipeng Fan, Ming Chen, Zeguo Qiu (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-12787720.txt.
Description
Wei Liu and co-authors build a light detector for rice leaf disease that can run on field devices in a 2025 study. Rice disease cuts yield, and field photos are hard, with tiny spots, uneven light, and cluttered scenes. A model must be both accurate and small enough for edge hardware, so the team reworked a known detector.
They swapped in a lighter backbone, added a part for fine detail at many scales, and added a head that finds small spots better. They then pruned parts and used teaching from a larger model to regain quality. The shrunk model took little storage, scored high on a public data set, and ran fast in their tests.
Catalog record
| CREATOR | Wei Liu, Baoquan Duan, Zhipeng Fan, Ming Chen, Zeguo Qiu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 39 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |