MAR-YOLO: multi-scale feature adaptive selection and asymptotic pyramid for oriented Building detection in remote sensing images
Yuzhe Zhao, Haizhong Qian · 2025
Read MAR-YOLO: multi-scale feature adaptive selection and asymptotic pyramid for oriented Building detection in remote sensing images by Yuzhe Zhao, Haizhong Qian (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-12835050.txt.
Description
Yuzhe Zhao and Haizhong Qian build a better building finder for aerial images in a paper from 2025. Remote sensing photos show buildings at many sizes, often tilted by the camera angle. Older detectors handle each problem alone and falter when problems combine. Their system, MAR-YOLO, extends a popular detector with three linked upgrades.
One part picks the most useful image features at each scale. A second part blends those features step by step to keep meanings aligned. A third part steadies the angle estimates for rotated buildings. On a standard test set the system beat its base model on accuracy while running fast. Tests on three more sets confirmed the design held up.
Catalog record
| CREATOR | Yuzhe Zhao, Haizhong Qian |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 69 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |