RFPruning: A retraining-free pruning method for accelerating convolutional neural networks
Authors:
- Zhenyu WangZWZhenyu Wang
- Xuemei XieXuemei Xie
- Guangming ShiGSGuangming Shi
- 1 December 2021
- journal article
- research article
- Published by Elsevier in Applied Soft Computing
- Vol. 113
Abstract
No abstract availableKeywords
Funding Information
- National Key Research and Development Program of China (2020AAA0109301)
- National Natural Science Foundation of China (61632019)
- National Natural Science Foundation of China (61836008)
This publication has 21 references indexed in Scilit:
- ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression2017
- Learning Efficient Convolutional Networks through Network Slimming2017
- Channel Pruning for Accelerating Very Deep Neural Networks2017
- Densely Connected Convolutional Networks2017
- Deep Residual Learning for Image Recognition2016
- Going deeper with convolutions2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Fixed point optimization of deep convolutional neural networks for object recognition2015
- Roulette-wheel selection via stochastic acceptancePhysica A: Statistical Mechanics and its Applications, 2012
- Distributed Optimization and Statistical Learning via the Alternating Direction Method of MultipliersFoundations and Trends in Machine Learning, 2011