LE-PWDNet: a lightweight and enhanced detection framework based on DEIM for early-stage pine wilt disease
Yujia Shen, Fang Wang, Jingjing Qian, Haifeng Lin · 2025
Read LE-PWDNet: a lightweight and enhanced detection framework based on DEIM for early-stage pine wilt disease by Yujia Shen, Fang Wang, Jingjing Qian, Haifeng Lin (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-12750628.txt.
Description
Pine wilt disease races through forests and kills fast, and catching it early means spotting tiny lesions in messy canopy photographs. Yujia Shen and co-authors build a lightweight detector for drone surveys in a 2025 paper. Their training set holds over forty-one thousand high-resolution images covering four infection stages.
The model adds several custom parts to a modern detection framework: a wavelet-based convolution for fine lesion texture, and a fusion module that resists background noise. An adaptive sampler also preserves edge detail. Each piece targets a known failure of small-object detection in complex forest scenes. The authors aim for accuracy a field team can actually carry: high precision without a heavyweight model. Early, cheap detection is the lever that slows the spread of the disease.
Catalog record
| CREATOR | Yujia Shen, Fang Wang, Jingjing Qian, Haifeng Lin |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 77 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |