Exploiting Channel Similarity for Network Pruning-Reference-Cited by-同舟云学术

Exploiting Channel Similarity for Network Pruning

Published:2023-09 Issue:9 Volume:33 Page:5049-5061
ISSN:1051-8215
Container-title:IEEE Transactions on Circuits and Systems for Video Technology
language:
Short-container-title:IEEE Trans. Circuits Syst. Video Technol.

Author:

Zhao Chenglong¹^ORCID,Zhang Yunxiang²^ORCID,Ni Bingbing¹^ORCID

Affiliation:

1. School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China

2. Tandon School of Engineering, New York University, Brooklyn, NY, USA

Funder

National Science Foundation of China

Shanghai Jiao Tong University Medical Engineering Cross Research

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Media Technology

Link

http://xplorestaging.ieee.org/ielx7/76/10241245/10052713.pdf?arnumber=10052713

Reference71 articles.

1. XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

2. The average spearman rank correlation coefficient

3. Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or ?1;courbariaux;arXiv 1602 02830 [cs],2016

4. THE TREATMENT OF TIES IN RANKING PROBLEMS

5. Neural architecture search with reinforcement learning;zoph;Proc Int Conf Learn Represent,2017

Cited by 5 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. Cross-layer importance evaluation for neural network pruning;Neural Networks;2024-11

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

3. PSE-Net: Channel pruning for Convolutional Neural Networks with parallel-subnets estimator;Neural Networks;2024-06

4. ARPruning: An automatic channel pruning based on attention map ranking;Neural Networks;2024-06

5. V-SKP: Vectorized Kernel-Based Structured Kernel Pruning for Accelerating Deep Convolutional Neural Networks;IEEE Access;2023