Channel pruning on frequency response  

作　　者：Hang LIN Yifan PENG Lin BIE Chenggang YAN Xibin ZHAO Yue GAO 

机构地区：[1]School of Software,Tsinghua University,Beijing 100084,China [2]School of Automation,Hangzhou Dianzi University,Hangzhou 310012,China

出　　处：《Science China(Information Sciences)》2025年第1期156-167,共12页中国科学(信息科学)(英文版)

基　　金：supported by National Natural Science Foundation of China(Grant Nos.U20A6003,62076146,62021002,U19A2062,U1911401,6212780016);Industrial Technology Infrastructure Public Service Platform Project,Ministry of Industry and Information Technology of China(Grant No.2022-233-225).

摘　　要：Network pruning has a significant role in reducing network parameters and accelerating the inference time of the network.Some existing methods prune the network based on the frequency of the data,and finally obtain a sub-network with high accuracy.However,according to our experimental analysis,different frequencies of information in the data contribute differently to the accuracy of the model,and using this information directly for pruning without making a selection will lead to incorrect results.We believe that pruning should retain the convolutional kernels in the network that process important information,while those kernels that process unimportant information should be removed.In this paper,we first investigate the meaning of each frequency band information in the spectrum and their contribution to the prediction accuracy of the network,and according to these results,we propose a new pruning method based on frequency response(PFR).Our PFR finds and removes the convolutional kernels in the network that specialize in processing unimportant information,resulting in a compact neural network model.PFR obtains significant experimental results on different datasets,for example,a 56.0%raduction of float points operations(FLOPs)on ResNet-50 and only 0.37%of Top-1 accuracy degradation on the ImageNet dataset.

关 键 词：deep learning model compression filter pruning channel pruning frequency response 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]