Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction-Reference-Cited by-同舟云学术

Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction

Published:2022-06 Issue: Volume: Page:
ISSN:
Container-title:2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Elkerdawy Sara¹,Elhoushi Mostafa²,Zhang Hong¹,Ray Nilanjan¹

Affiliation:

1. University of Alberta,Huawei

2. Toronto Heterogeneous Compilers Lab,Huawei

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9878378/9878366/09879188.pdf?arnumber=9879188

Reference47 articles.

1. MnasNet: Platform-Aware Neural Architecture Search for Mobile

2. Very deep convolutional networks for large-scale image recognition;simonyan;3rd International Conference on Learning Representations ICLR 2015,2015

3. Piggy- back: Adapting a single network to multiple tasks by learning to mask weights;mallya;Proceedings of the European Conference on Computer Vision (ECCV),0

4. ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression

5. Selection of Intrinsic Horizontal Connections in the Visual Cortex by Correlated Neuronal Activity

Cited by 21 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. Self-supervised feature-gate coupling for dynamic network pruning;Pattern Recognition;2024-10

2. Efficient filter pruning: Reducing model complexity through redundancy graph decomposition;Neurocomputing;2024-09

3. Attention-based adaptive structured continuous sparse network pruning;Neurocomputing;2024-07

4. Multi-resolution Neural Network Compression Based on Variational Bayesian Inference;ICC 2024 - IEEE International Conference on Communications;2024-06-09

5. Adapting Neural Networks at Runtime: Current Trends in At-Runtime Optimizations for Deep Learning;ACM Computing Surveys;2024-05-14