Selective Pruning
Selective Pruning is a model compression technique that systematically removes less informative neural network parameters based on sensitivity analysis to preserve critical model functionality while reducing computational complexity.
65
Publications
3.3K
Citations
213
Authors
107
Institutions
Publications per year
2017–2026
34
65
DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
Yongming Rao, Wenliang Zhao, Benlin Liu et al. · arXiv (Cornell University) · 2021 · 310 citations · Full text
Learning to Prune Filters in Convolutional Neural Networks
Qiangui Huang, Kevin Zhou, Suya You et al. · 2018 · 166 citations
1–5 of 65
213
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 213
107
Louisiana State University
Baton Rouge, United States
2 h-index
4 publications
104 citations
University of Chinese Academy of Sciences
Beijing, China
2 h-index
5 publications
178 citations
National University of Singapore
Singapore, Singapore
2 h-index
2 publications
60 citations
IMT Atlantique
Nantes, France
1 h-index
4 publications
108 citations

Vilnius Gediminas Technical University
Vilnius, Lithuania
1 h-index
2 publications
26 citations

Fulda University of Applied Sciences
Fulda, Germany
1 h-index
1 publications
37 citations
Information Technology University
Lahore, Pakistan
1 h-index
1 publications
57 citations
Association of Electronic and Information Technologies
Donostia / San Sebastian, Spain
1 h-index
2 publications
106 citations
1–8 of 107
Repository · 11 publications · 703 citations
11
h-index
3 publications · 121 citations
3
h-index
1 publications · 476 citations
1
h-index
1 publications · 27 citations
1
h-index
1 publications · 17 citations
1
h-index
1–5