[1]YIN Rui,SU Songzhi,LI Shaozi.Convolutional neural network’s image moment regularizing strategy[J].CAAI Transactions on Intelligent Systems,2016,11(1):43-48.[doi:10.11992/tis.201509018]
Copy
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
11
Number of periods:
2016 1
Page number:
43-48
Column:
学术论文—智能系统
Public date:
2016-02-25
- Title:
-
Convolutional neural network’s image moment regularizing strategy
- Author(s):
-
YIN Rui1; 2; SU Songzhi1; 2; LI Shaozi1; 2
-
1. School of Information Science and Technology, Xiamen University, Xiamen 361005, China;
2. Fujian Key Laboratory of the Brain-Like Intelligent System, Xiamen University, Xiamen 361005, China
-
- Keywords:
-
central moment; random selection; pooling; convolutional neural network; overfitting
- CLC:
-
TP391.4
- DOI:
-
10.11992/tis.201509018
- Abstract:
-
There are two kinds of pooling strategies for convolutional neural network (CNN) as follows: max pooling and average pooling. Max pooling simply chooses the maximum element, which makes this strategy extremely prone to overfitting. Average pooling endows all elements with the same weight, which lowers the weight of the high-frequency components. In this study, we propose moment pooling as a regularization strategy for CNN. First, we introduce the geometric moment to CNN pooling and calculate the central moment of the pooling region. Then, we randomly select the response values based on the probability-like interpolation method from the four neighbors of the moment as per their probability. Experiments on the MNIST, CIFAR10, and CIFAR100 datasets show that moment pooling obtains the fewest training and test errors with training iteration increments. This strategy’s robustness and strong discrimination capability yield better generalization results than those from the max and average pooling methods.