MLE-YOLOv11n: Multi-scale layer aggregation and context-aware feature fusion for insulator defect detection in aerial imagery
Yuan Wang, Hanzhi Cui, Jinxian Li, Zongxiu Duan, Qiqi Wei · 2026
Read MLE-YOLOv11n: Multi-scale layer aggregation and context-aware feature fusion for insulator defect detection in aerial imagery by Yuan Wang, Hanzhi Cui, Jinxian Li, Zongxiu Duan, Qiqi Wei (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-0354898.txt.
Description
Yuan Wang and four colleagues published this 2026 computer vision paper on finding defects in power line insulators from drone photos. Damaged insulators can spark, flash over, or fail, but in aerial images the parts are tiny and backgrounds are cluttered. Their detector rebuilds a lightweight detection model with three swapped-in modules for richer scale and context handling.
The upgraded model caught more of the rare, awkward defect types that the base model missed. It stayed fast enough for live inspection work and grew only modestly in size. Wang's team sees it as a candidate for inspection gear that runs on modest onboard hardware.
Catalog record
| CREATOR | Yuan Wang, Hanzhi Cui, Jinxian Li, Zongxiu Duan, Qiqi Wei |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 79541 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |