Channel pruning based on convolutional neural network sensitivity
Authors:
- Chenbin YangCYChenbin Yang
- Huiyi LiuHLHuiyi Liu
- 1 August 2022
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 507, 97-106
Abstract
No abstract availableKeywords
Funding Information
- Ministry of Science and Technology of the People's Republic of China
- National Key Research and Development Program of China (2019YFE0105200)
- National Natural Science Foundation of China
This publication has 21 references indexed in Scilit:
- Multi-Scale Dynamic Convolutional Network for Knowledge Graph EmbeddingIEEE Transactions on Knowledge and Data Engineering, 2020
- HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision2019
- Play and Prune: Adaptive Filter Pruning for Deep Model Compression2019
- Importance Estimation for Neural Network Pruning2019
- Data-Driven Sparse Structure Selection for Deep Neural Networks2018
- Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference2018
- On Compressing Deep Models by Low Rank and Sparse Decomposition2017
- Channel-level acceleration of deep face representationsIEEE Access, 2015
- ImageNet: A large-scale hierarchical image database2009
- Power Iteration Method for the Several Largest Eigenvalues and EigenfunctionsNuclear Science and Engineering, 2006