YOLO-LitchiVar: a lightweight and high-precision detection model for fine-grained litchi variety identification
Bing Xu, Xianjun Wu, Xueping Su, Wende Ke · 2026
Read YOLO-LitchiVar: a lightweight and high-precision detection model for fine-grained litchi variety identification by Bing Xu, Xianjun Wu, Xueping Su, Wende Ke (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-12894316.txt.
Description
Bing Xu, Xianjun Wu, Xueping Su, and Wende Ke present a light vision model that tells litchi types apart, in a paper listed as 2026. Litchi fruit comes in about one hundred types, and sorting by hand after harvest is slow and prone to error. Fine traits on the skin are easy to miss.
The team built a photo set for twelve common market types and tuned a fast detector for the task. Three new parts cut model size, sharpen fine skin detail, and lift recall for a hard type with faint dents. The result is both smaller and more precise than the base model, which suits sorting lines and handheld tools.
Catalog record
| CREATOR | Bing Xu, Xianjun Wu, Xueping Su, Wende Ke |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 84 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |