Channel Pruning Method Based on Decoupling Feature Scale Distribution in Batch Normalization Layers

Channel Pruning Method Based on Decoupling Feature Scale Distribution in Batch Normalization Layers

Pruning and compression of models are practical approaches for deploying and applying deep convolutional neural networks in scenarios with limited memory and computational resources. To mitigate the impact of pruning on model accuracy and enhance the stability of pruning (defined as the negligible d...

Full description

Bibliographic Details
Main Authors: Zijie Qiu, Peng Wei, Mingwei Yao, Rui Zhang, Yingchun Kuang
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Neural network
structured pruning
model compression
neural network lightweighting
automatic pruning
pruning stability
Online Access:https://ieeexplore.ieee.org/document/10485421/

Internet

https://ieeexplore.ieee.org/document/10485421/

Similar Items