Coordinate aware implicit neural representation for UAV small object detection
Yong Yang, Tianci Wan, Ling Guo, Menglu Zhang · 2026
Read Coordinate aware implicit neural representation for UAV small object detection by Yong Yang, Tianci Wan, Ling Guo, Menglu Zhang (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-0350990.txt.
Description
Yong Yang and colleagues improve how drones spot very small objects from the air. Tiny targets fill few pixels, sit in busy scenes, and shift scale fast, so fixed window detectors miss detail. Their module feeds map coordinates into the detector at several scales, blends them with image features, and adds attention that favours small, sharp targets.
Tests on three drone image sets showed steady gains over strong rivals, with little added computing cost. A test on a general photo set also held up, which hints at wide use. Sharper small object spotting helps traffic watching, search work, and crop scouting, where the key detail is often the smallest thing in frame.
Catalog record
| CREATOR | Yong Yang, Tianci Wan, Ling Guo, Menglu Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49930 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |