Research on an improved RT-DETR-based model for rice disease detection
Yaojun Zhang, Changqiang Shen, Ying Xiong · 2026
Read Research on an improved RT-DETR-based model for rice disease detection by Yaojun Zhang, Changqiang Shen, Ying Xiong (2026) 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/plos-pone-0349237.txt.
Description
Yaojun Zhang, Changqiang Shen, and Ying Xiong improved a computer vision model for spotting rice diseases in 2026. Finding and locating disease early protects harvests, yet field images are cluttered, lesions are small, and heavy models run slowly.
Their model swaps in a light backbone that reads fine detail cheaply, uses an upsampling step that keeps detail, and adds flexible convolution in the neck. Against the base model it gained a little accuracy, ran notably faster, and cut computing cost and size greatly. A lighter, quicker detector is what drones and farm phones can realistically carry.
Catalog record
| CREATOR | Yaojun Zhang, Changqiang Shen, Ying Xiong |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 56388 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |