Sensitivity pruner: Filter-Level compression algorithm for deep neural networks

•We integrate the sensitivity measure from SNIP into the “training while fine-tuning” framework to form a more powerful pruning strategy by adapting the unstructured pruning measure from SNIP to allow filterlevel compression. In practice, the sensitivity score can be easily computed as the gradient...

Full description

Bibliographic Details

Published in:	Pattern recognition Vol. 140; p. 109508
Main Authors:	Guo, Suhan, Lai, Bilan, Yang, Suorong, Zhao, Jian, Shen, Furao
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 01.08.2023
Subjects:	End-to-end pruning framework Filter pruning Saliency-based pruning Sampling bias End-to-end pruning framework Sampling bias Saliency-based pruning Filter pruning
ISSN:	0031-3203, 1873-5142
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!