Laser weld spot detection based on YOLO-weld
Jianxin Feng, Jiahao Wang, Xinyu Zhao, Zhiguo Liu, Yuanming Ding · 2024
Read Laser weld spot detection based on YOLO-weld by Jianxin Feng, Jiahao Wang, Xinyu Zhao, Zhiguo Liu, Yuanming Ding (2024) 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-11599603.txt.
Description
Jianxin Feng and four co-authors build a leaner vision model to spot laser weld points in factory work, in a paper from 2024. Weld point checks face few samples, skewed class counts, and spots in many odd shapes.
Their model, YOLO-weld, first grows rare class samples with targeted tweaks, then trains with new loss terms that stress rare and mid grade cases. A light multi scale block trims size while it sharpens features at varied scales. In tests the model raised key scores by wide margins over the base form, while using fewer weights and less compute.
Catalog record
| CREATOR | Jianxin Feng, Jiahao Wang, Xinyu Zhao, Zhiguo Liu, Yuanming Ding |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 93 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |