Cargando…
HMC: Hybrid model compression method based on layer sensitivity grouping
Previous studies have shown that deep models are often over-parameterized, and this parameter redundancy makes deep compression possible. The redundancy of model weight is often manifested as low rank and sparsity. Ignoring any part of the two or the different distributions of these two characterist...
Autores principales: | Yang, Guoliang, Yu, Shuaiying, Yang, Hao, Nie, Ziling, Wang, Jixiang |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10561844/ https://www.ncbi.nlm.nih.gov/pubmed/37812605 http://dx.doi.org/10.1371/journal.pone.0292517 |
Ejemplares similares
-
A Multi-Scale Dehazing Network with Dark Channel Priors
por: Yang, Guoliang, et al.
Publicado: (2023) -
The HMC project
por: Bradamante, Franco
Publicado: (1995) -
Attention and feature transfer based knowledge distillation
por: Yang, Guoliang, et al.
Publicado: (2023) -
Author Correction: Attention and feature transfer based knowledge distillation
por: Yang, Guoliang, et al.
Publicado: (2023) -
A simple method to optimize HMC performance
por: Bussone, Andrea, et al.
Publicado: (2016)