.png){kind=icon}
.png){kind=icon}
Return
An Efficient Sharing Grouped Convolution via Bayesian Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2021.3084900.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Compared with traditional convolutions, grouped convolutional neural networks are promising for both model performance and network parameters. However, existing models with the grouped convolution still have parameter redundancy. In this article, concerning the grouped convolution, we propose a sharing grouped convolution structure to reduce parameters. To efficiently eliminate parameter redundancy and improve model performance, we propose a Bayesian sharing framework to transfer the vanilla grouped convolution to be the sharing structure. Intragroup correlation and intergroup importance are introduced into the prior of the parameters. We handle the Maximum Type II likelihood estimation problem of the intragroup correlation and intergroup importance by a group LASSO-type algorithm. The prior mean of the sharing kernels is iteratively updated. Extensive experiments are conducted to demonstrate that on different grouped convolutional neural networks, the proposed sharing grouped convolution structure with the Bayesian sharing framework can reduce parameters and improve prediction accuracy. The proposed sharing framework can reduce parameters up to 64.17%. For ResNeXt-50 with the sharing grouped convolution on ImageNet dataset, network parameters can be reduced by 96.875% in all grouped convolutional layers, and accuracies are improved to 78.86% and 94.54% for top-1 and top-5, respectively.
Keywords:
Convolution
Computational modeling
Redundancy
Bayes methods
Kernel
Correlation
Training
Bayesian inference
convolutional neural networks (CNNs)
grouped convolution
LASSO
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W