Accelerating Convolutional Networks via Global & Dynamic Filter Pruning

Author:

Lin Shaohui12,Ji Rongrong12,Li Yuchao12,Wu Yongjian3,Huang Feiyue3,Zhang Baochang4

Affiliation:

1. Fujian Key Laboratory of Sensing and Computing for Smart City, Xiamen University, China

2. School of Information Science and Engineering, Xiamen University, China

3. BestImage, Tencent Technology (Shanghai) Co.,Ltd, China

4. School of Automation Science and Electrical Engineering, Beihang University, China

Abstract

Accelerating convolutional neural networks has recently received ever-increasing research focus. Among various approaches proposed in the literature, filter pruning has been regarded as a promising solution, which is due to its advantage in significant speedup and memory reduction of both network model and intermediate feature maps. To this end, most approaches tend to prune filters in a layer-wise fixed manner, which is incapable to dynamically recover the previously removed filter, as well as jointly optimize the pruned network across layers. In this paper, we propose a novel global & dynamic pruning (GDP) scheme to prune redundant filters for CNN acceleration. In particular, GDP first globally prunes the unsalient filters across all layers by proposing a global discriminative function based on prior knowledge of filters. Second, it dynamically updates the filter saliency all over the pruned sparse network, and then recover the mistakenly pruned filter, followed by a retraining phase to improve the model accuracy. Specially, we effectively solve the corresponding non-convex optimization problem of the proposed GDP via stochastic gradient descent with greedy alternative updating. Extensive experiments show that, comparing to the state-of-the-art filter pruning methods, the proposed approach achieves superior performance to accelerate several cutting-edge CNNs on the ILSVRC 2012 benchmark.

Publisher

International Joint Conferences on Artificial Intelligence Organization

Cited by 80 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Building efficient CNNs using Depthwise Convolutional Eigen-Filters (DeCEF);Neurocomputing;2024-12

2. ResPrune: An energy-efficient restorative filter pruning method using stochastic optimization for accelerating CNN;Pattern Recognition;2024-11

3. Iterative filter pruning with combined feature maps and knowledge distillation;International Journal of Machine Learning and Cybernetics;2024-09-06

4. A Review on the emerging technology of TinyML;ACM Computing Surveys;2024-06-22

5. DBS: Differentiable Budget-Aware Searching For Channel Pruning;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3