Regularization of convolutional neural networks using ShuffleNode

Yihao Chen, Hanli Wang, Yu Long

Abstract

Convolutional Neural Network (CNN) has recently achieved significant performances for visual computing, and a number of researches are made to explore advanced model structures to solve the problem of over-fitting. In this paper, a regularization technique named ShuffleNode is proposed, which shuffles feature map elements to achieve regularization functions during model training. Specifically, there are two shuffle ways including within-map shuffle and cross-map shuffle, which are suitable to be employed in convolutional layers. The method of within-map shuffle is used to provide the exchange of elements within one feature map, while the cross-map shuffle method offers the opportunity of information sharing across different feature maps. The experimental results on several benchmark image classification datasets demonstrate the efficiency of the proposed method.
BibTeX
@inproceedings{chen2017regularization,
  author = {Yihao Chen and Hanli Wang and Yu Long},
  title = {{Regularization of convolutional neural networks using ShuffleNode}},
  booktitle = {ICME},
  year = {2017},
  doi = {10.1109/icme.2017.8019402},
}

Loading related content...

Figure