logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Soft-label generator based on classifier weights

delete2025-09-09
delete0
PRE
AI
X
Xinkai Chu
J
Jian-Ping Mei *
H
Hang Zhou
陈
陈杰 (Jie Chen)
R
Rui-Jun Yan
J
Jing Fan
DOI：10.1016/j.neucom.2025.131436delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• Use self-derived soft labels as additional signals for classification model training. • Propose a generic, small overhead, and easy-to-implement soft-label generator. • Realize a unified formulation of class-level semantics and instance-level uncertainty. • Apply to both teacher-free and teacher-available scenarios. • Provide experimental results on image classification under various supervised settings.

Journal

Neurocomputing cover
Neurocomputing
IF:
6.5
Papers:
2.5W
Citations:
6.5W

Organization

No organization information available