WSD-YOLO: A lightweight YOLO-based model with enhanced feature representation for maize pest detection
Shenming Qu, Zhiheng Liu, Huazhen Zhao, Yichao Wu, Yang Yang · 2026
Read WSD-YOLO: A lightweight YOLO-based model with enhanced feature representation for maize pest detection by Shenming Qu, Zhiheng Liu, Huazhen Zhao, Yichao Wu, Yang Yang (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/pmc-13577518.txt.
Description
Shenming Qu, Zhiheng Liu, Huazhen Zhao, Yichao Wu, and Yang Yang published a computer vision study in twenty twenty-six on spotting maize pests in field photos. Pests change shape as they grow and hide against messy backgrounds, so detectors miss them. The team rebuilt a lightweight YOLO model with three new modules and named it WSD-YOLO.
One module sharpens sensitivity to pest textures from several directions. A transformer block adds global attention to suppress background noise cheaply. A dual-attention module blends features so varied pest shapes register. Across repeated training runs on a maize pest dataset, the model averaged about seventy-nine percent mean average precision. The design targets accurate scouting without heavy computing.
Catalog record
| CREATOR | Shenming Qu, Zhiheng Liu, Huazhen Zhao, Yichao Wu, Yang Yang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 78 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |