Filter Level Pruning Based on Similar Feature Extraction for Convolutional Neural Networks

Lianqiang LI  Yuhui XU  Jie ZHU  

IEICE TRANSACTIONS on Information and Systems   Vol.E101-D   No.4   pp.1203-1206
Publication Date: 2018/04/01
Publicized: 2018/01/18
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2017EDL8248
Type of Manuscript: LETTER
Category: Artificial Intelligence, Data Mining
CNNs,  filter,  pruning,  feature extraction,  k-means++,  structured,  

Full Text: PDF(177.1KB)>>
Buy this Article

This paper introduces a filter level pruning method based on similar feature extraction for compressing and accelerating the convolutional neural networks by k-means++ algorithm. In contrast to other pruning methods, the proposed method would analyze the similarities in recognizing features among filters rather than evaluate the importance of filters to prune the redundant ones. This strategy would be more reasonable and effective. Furthermore, our method does not result in unstructured network. As a result, it needs not extra sparse representation and could be efficiently supported by any off-the-shelf deep learning libraries. Experimental results show that our filter pruning method could reduce the number of parameters and the amount of computational costs in Lenet-5 by a factor of 17.9× with only 0.3% accuracy loss.