Confusion matrix of YOLOv8n.

<div><p>Standard detectors such as YOLOv8 face significant challenges when applied to aerial drone imagery, including extreme scale variations, minute targets, and complex backgrounds. Their generic feature fusion architecture is prone to generating false positives and missing small obje...

Full description

Saved in:

Bibliographic Details
Main Author:	Dan Tian (697937) (author)
Other Authors:	Xiao Wang (19312) (author), Dongxin Liu (751135) (author), Ying Hao (32779) (author)
Published:	2025
Subjects:	Biotechnology Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified wiouv3 loss function task representation optimization strengthen feature representation multiscale feature fusion missing small objects level feature interactions aerial drone imagery model &# 8217 baseline yolov8n model maintains detection accuracy generating false positives scale feature interaction distinguish small targets stage partial network dynamic alignment network efficiently propagate multi depth convolution module yolo model based model introduces scale targets false negative detection head based intra scale features minute targets neck network backbone network yolov13 across yolo surpasses reduces parameters nwpu vhr kernel module insufficient synergy image recovery focusing coefficients dynamically adjust deep layers computational burden complex backgrounds classification tasks art methods 10 datasets
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Confusion matrix of YOLOv8n.

Similar Items