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

Maximum redundancy pruning for network compression

delete2025-06-10
delete0
PRE
AI
C
Chang Gao
J
Jiaqi Wang
景
景丽萍 (Liping Jing) *
DOI：10.1016/j.cviu.2025.104404delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• We propose a layer redundancy hypothesis with cross-dataset applicability. • MRP enables optimal layer-wise pruning without predefined ratios or extra tuning. • Node centrality metric maximizes information retention in filter selection.
Keywords:
layer redundancy
model pruning
node centrality
filter selection
cross-dataset applicability

Journal

Computer Vision and Image Understanding cover
Computer Vision and Image Understanding
IF:
3.5
Papers:
428
Citations:
7.3K

Organization

No organization information available