Progressive multi-level distillation learning for pruning network

Abstract Although the classification method based on the deep neural network has achieved excellent results in classification tasks, it is difficult to apply to real-time scenarios because of high memory footprints and prohibitive inference times. Compared to unstructured pruning, structured pruning...

Description complète

Détails bibliographiques

Auteurs principaux:	Ruiqing Wang, Shengmin Wan, Wu Zhang, Chenlu Zhang, Yu Li, Shaoxiang Xu, Lifu Zhang, Xiu Jin, Zhaohui Jiang, Yuan Rao
Format:	Artigo
Langue:	Inglês
Publié:	Springer 2023-04-01
Collection:	Complex & Intelligent Systems
Sujets:	Deep neural network Model compression Network pruning Knowledge distillation
Accès en ligne:	https://doi.org/10.1007/s40747-023-01036-0
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!