arrow
Return

Learning to complement with multiple humans

delete2025-09-01
delete0
PRE
AI
Z
Zheng Zhang
C
Cuong C. Nguyen
K
Kevin Wells
T
Thanh-Toan Do
G
Gustavo Carneiro
DOI:10.1016/j.patcog.2025.112376delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• New learning to complement method called LECOMH. • LECOMH maximises human-AI accuracy while minimising the cost of human collaboration. • LECOMH integrates noisy label learning and multi-rater learning. • The paper presents new benchmarks to assess human-AI collaborative methods.

Journal

Pattern Recognition cover
Pattern Recognition
IF:
7.6
Papers:
1.3W
Citations:
4.5W

Organization

M
Monash University
Scholars:
5.4W
Papers: 5.4W
Citations: 79
U
University of Surrey
Scholars:
1.2W
Papers: 1.3W
Citations: 22