RFPruning: A retraining-free pruning method for accelerating convolutional neural networks
RFPruning: A retraining-free pruning method for accelerating convolutional neural networks
复制标题
RFPruning：一种用于加速卷积神经网络的免重训练剪枝方法
DOI：
10.1016/j.asoc.2021.107860
复制
发表时间：
2021-09
影响因子：
8.7
通讯作者：
Guangming Shi
中科院分区：
文献类型：
--
作者：
Zhenyu Wang;Xuemei Xie;Guangming Shi
Network pruning has been developed as a remedy for accelerating the inference of deep convolutional neural networks (DCNNs). The mainstream methods retrain the pruned models, which maintain the performance of the pruned models but consume a great deal of time. While the other methods reduce the time consumption by omitting to retrain, they lose the performance. To resolve the above conflicts, we propose a two-stage Retraining-Free pruning method, named RFPruning, which embeds the rough screening of channels into training and fine-tunes the structures during pruning, to achieve both good performance and low time consumption. In the first stage, the network training is reformulated as an optimization problem with constraints and solved by a sparse learning approach for rough channel selection. In the second stage, the pruning process is regarded as a multiobjective optimization problem, where the genetic algorithm is applied to carefully select channels for a trade-off between the performance and model size. The proposed method is evaluated against several DCNNs on CIFAR-10 and ImageNet datasets. Extensive experiments demonstrate that such a retraining-free pruning method obtains 43.0%∼ 88.4% compression on model size and maintains the accuracy as the methods with retraining while achieving 3× speed up in pruning.
登录
查看更多内容
DOI：
--
发表时间：
2015-04
期刊：
ArXiv
影响因子：
--
作者：
Wenlin Chen-;James T. Wilson;Stephen Tyree;Kilian Q. Weinberger;Yixin Chen
通讯作者：
Wenlin Chen-;James T. Wilson;Stephen Tyree;Kilian Q. Weinberger;Yixin Chen
DOI：
10.1109/cvpr.2019.01146
发表时间：
2018-12
期刊：
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子：
--
作者：
Haichuan Yang;Yuhao Zhu;Ji Liu
通讯作者：
Haichuan Yang;Yuhao Zhu;Ji Liu
DOI：
10.1016/s1474-6670(17)38315-5
发表时间：
1998-10
期刊：
--
影响因子：
--
作者：
A. Barto
通讯作者：
A. Barto
DOI：
--
发表时间：
2016-06
期刊：
ArXiv
影响因子：
--
作者：
Shuchang Zhou;Zekun Ni;Xinyu Zhou;He Wen;Yuxin Wu;Yuheng Zou
通讯作者：
Shuchang Zhou;Zekun Ni;Xinyu Zhou;He Wen;Yuxin Wu;Yuheng Zou
DOI：
10.1609/aaai.v34i04.5924
发表时间：
2019-07
期刊：
--
影响因子：
--
作者：
Ning Liu;Xiaolong Ma;Zhiyuan Xu;Yanzhi Wang;Jian Tang;Jieping Ye
通讯作者：
Ning Liu;Xiaolong Ma;Zhiyuan Xu;Yanzhi Wang;Jian Tang;Jieping Ye