Performance of TLINet, YOLOv8, YOLOv9 and YOLOv10 on Insulator-DET dataset.

<p>Performance of TLINet, YOLOv8, YOLOv9 and YOLOv10 on Insulator-DET dataset.</p>

Saved in:

Bibliographic Details
Main Author:	Xun Li (182737) (author)
Other Authors:	Yuzhen Zhao (2743177) (author), Yang Zhao (39052) (author), Zhun Guo (10381065) (author), Yongming Zhang (1518268) (author), Xiangke Jiao (21602201) (author), Baoxi Yuan (14441925) (author)
Published:	2025
Subjects:	Medicine Sociology Science Policy Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified power transmission lines module enables fine generate adaptive responses complex natural environments insulator defect detection insulators exhibit characteristics dynamic downsampling module div >< p defects detection method capturing global features 1 %, respectively tlinet improves map50 small object sizes various sizes complex backgrounds achieves map50 insulator defects constructed insulator tlinet </ scale variations results demonstrate proposed algorithm pressing challenge paper proposes grained fusion different scales det dataset cgffn ). backbone ’ accurately focusing 95 improvements
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items