Channel Pruning via Multi-Criteria based on Weight Dependency

Channel pruning has demonstrated its effectiveness in compressing ConvNets. In many related arts, the importance of an output feature map is only determined by its associated filter. However, these methods ignore a small part of weights in the next layer which disappears as the feature map is removed. They ignore the phenomenon of weight dependency. Besides, many pruning methods use only one criterion for evaluation and find a sweet spot of pruning structure and accuracy in a trial-and-error fashion, which can be time-consuming. In this paper, we proposed a channel pruning algorithm via multi-criteria based on weight dependency, CPMC, which can compress a pre-trained model directly.

Data and Resources

Cite this as

Yangchun Yan, Rongzuo Guo, Chao Li, Kang Yang, Yongjun Xu (2024). Dataset: Channel Pruning via Multi-Criteria based on Weight Dependency. https://doi.org/10.57702/zbajc4ej

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Author Yangchun Yan
More Authors
Rongzuo Guo
Chao Li
Kang Yang
Yongjun Xu
Homepage https://arxiv.org/abs/2006.11144