.png){kind=icon}
返回
CorrNet: pearson correlation based pruning for efficient convolutional neural networks
.png){kind=icon}
PRE
AI
DOI：10.1007/s13042-022-01624-5.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Convolutional neural networks (CNNs) are quickly evolving, which usually results in a surge of computational cost and model size. In this article, we present a correlation-based filter pruning (CFP) approach to train more reliable CNN models. Unlike several available filter pruning methodologies, our presented approach eliminates useless filters according to the volume of information available in their related feature maps. We apply correlation to compute the duplication of information carried in the feature maps and created a feature selection scheme to obtain pruning approaches. Pruning and fine-tuning are cycled many times, producing slim and denser networks with similar accuracy to the original unpruned model. We practically calculate the success of our technique with various state-of-art CNN models on many standard datasets. Specifically, for ResNet-50 on ImageNet, our approach eliminates 44.6% filter weights and saves 51.6% Float-Point-Operations (FLOPs) with 0.5% accuracy gain and obtained state-of-art performance.
Keyword:
Correlation
Feature maps
FLOPs
ResNet
ImageNet
期刊
IF:
2.7
论文数:
3.2K
被引数:
5.6K
机构
引用论文
Management strategies for complex sedimentation process: a case study using remote sensing and morpho-dynamics simulation at Damietta Harbour, Nile Delta复杂沉积过程的治理策略：以尼罗河三角洲达米埃塔港的遥感与形态动力学模拟为例
PREAI
分享收藏
A Hierarchical Cardiac Rhythm Classification Methodology Based on Electrocardiogram Fiducial Points一种基于心电图基准点的分层心律分类方法
OAAI
OAAI分享收藏分享收藏Calcium-modulating cyclophilin ligand regulates membrane trafficking of postsynaptic GABAA receptorsOAAI
OAAI分享收藏Eighty Years of Targeting Androgen Receptor Activity in Prostate Cancer: The Fight Goes on.png)
CancersOAAI
CancersIF0
OAAI分享收藏Influence of carbon nanotube clustering on the electrical conductivity of polymer composite filmsOAAI
OAAI分享收藏
查看更多内容