Classification accuracy.

<div><p>Traditional uncertainty sampling methods in active learning often neglect category information, leading to imbalanced sample selection in multi-class computer vision tasks. Our approach integrates category information with uncertainty sampling through a novel active learning fram...

Full description

Saved in:

Bibliographic Details
Main Author:	Xiaochuan Wang (550306) (author)
Other Authors:	Bo Zhang (6559) (author), Fei Wang (19534) (author), Tao Bao (1454998) (author), Zhiqing Lu (17749008) (author), Jiawei Bao (17737830) (author)
Published:	2025
Subjects:	Space Science Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified trained vgg16 architecture scale data annotation reducing computational overhead maintaining computational efficiency limited labeled data imbalanced sample selection extensive experiments across cosine similarity metrics approach &# 8217 traditional uncertainty measures balance sampling efficiency method &# 8217 enhanced uncertainty sampling uncertainty sampling method employs work offers results validate object detection image classification framework combines efficient solution category information art approaches 80 %.
Tags:	Add Tag No Tags, Be the first to tag this record!

Classification accuracy.

Similar Items