一种基于特征导向解耦网络结构的滤波器修剪方法.pdfVIP

计算机研究与发展DOI：10.7544/issn1000-1239.202330085

Journal

of

Computer

Research

and

Development61（7）：1836−1849，2024

一种基于特征导向解耦网络结构的滤波器修剪方法

施瑞文李光辉代成龙张飞飞1112

1

（江南大学人工智能与计算机学院江苏无锡214122）

2

（江苏邦融微电子有限公司江苏昆山215300）

（srw0109@）

Feature-OrientedandDecoupledNetworkStructureBasedFilterPruningMethod

1

1

1

2

Shi

Ruiwen,

Li

Guanghui,

Dai

Chenglong,

and

Zhang

Feifei

1

（SchoolofArtificialIntelligenceandComputerScience,JiangnanUniversity,Wuxi,Jiangsu214122）

2

（JiangsuBangrongMicroelectronicsCo.,Ltd.,Kunshan,Jiangsu215300）

AbstractMany

existing

pruning

methods

for

deep

neural

network

models

require

modifying

the

loss

function

or

embedding

additional

variables

in

the

network,

thus

they

can’t

benefit

from

the

pre-trained

network

directly,

and

complicate

the

forward

inference

and

training

process.

So

far,

most

of

the

feature-oriented

pruning

work

only

use

the

intra-channel

information

to

analyze

the

importance

of

filters,

which

makes

it

impossible

to

use

the

potential

connections

among

channels

during

the

pruning

process.

To

address

these

issues,

we

consider

the

feature-oriented

filter

pruning

task

from

an

inter-channel

perspective.

The

proposed

method

uses

geometric

distance

to

measure

the

potential

correlation

among

channels,

defines

filter

pruning

as

an

optimization

problem,

and

applies

a

greedy

strategy

to

find

an

approximate

solution

to

the

optimal

solution.

The

method

achieves

the

decoupling

of

pruning

from

network

and

pruning

from

training,

thus

simplifying

the

pruning

task.

Extensive

experiments

demonstrate

that

the

proposed

pruning

method

achieves

high

perform