.png){kind=icon}
返回
Automatic filter pruning algorithm for image classification
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-023-05207-x.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Network pruning is an essential technique for compressing and accelerating convolutional neural networks (CNNs). Existing pruning algorithms primarily evaluate filter importance or similarity, and then remove unimportant filters or keep only one similar filter at each convolutional layer based on a global pruning ratio. These methods, ignoring the sensitivity of pruning among different convolutional layers, rely on a lot of manual experience and multiple experiments to obtain the optimal convolutional neural network structure. To this end, we propose an automatic filter pruning algorithm via feature map average similarity and reverse search genetic algorithm(RSGA), dubbed as AFPruner, which automatically searches for the optimal combination of pruning ratio for all convolutional layers, evaluates filter similarity by feature map average similarity and then prunes similarity filter. Our method is evaluated against several state-of-the-art CNNs on three different classification datasets, and the experimental results show that our algorithm outperforms most current network pruning algorithms.
Keyword:
Model compression
Convolutional neural network
Network pruning
Genetic algorithm
Feature map average similarity
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Calcium-modulating cyclophilin ligand regulates membrane trafficking of postsynaptic GABAA receptors
OAAI
OAAI分享收藏Filter pruning via separation of sparsity search and model training通过稀疏搜索和模型训练的分离进行滤波器修剪.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容