CondenseNet: An Efficient DenseNet Using Learned Group Convolutions

Deep neural networks are increasingly used on mobile devices, where computational resources are limited. In this paper we develop CondenseNet, a novel network architecture with unprecedented efficiency. It combines dense connectivity with a novel module called learned group convolution. The dense co...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 2752 - 2761
Main Authors Huang, Gao, Liu, Shichen, Maaten, Laurens van der, Weinberger, Kilian Q.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Computational modeling
Computer architecture
Indexes
Mobile handsets
Network architecture
Training
Online AccessGet full text

Cover

More Information
Summary:Deep neural networks are increasingly used on mobile devices, where computational resources are limited. In this paper we develop CondenseNet, a novel network architecture with unprecedented efficiency. It combines dense connectivity with a novel module called learned group convolution. The dense connectivity facilitates feature re-use in the network, whereas learned group convolutions remove connections between layers for which this feature re-use is superfluous. At test time, our model can be implemented using standard group convolutions, allowing for efficient computation in practice. Our experiments show that CondenseNets are far more efficient than state-of-the-art compact convolutional networks such as ShuffleNets.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00291