Interleaved Group Convolutions
Abstract
In this paper, we present a simple and modularized neural network architecture, named interleaved group convolutional neural networks (IGCNets). The main point lies in a novel building block, a pair of two successive interleaved group convolutions: primary group convolution and secondary group convolution. The two group convolutions are complementary: (i) the convolution on each partition in primary group convolution is a spatial convolution, while on each partition in secondary group convolution, the convolution is a point-wise convolution; (ii) the channels in the same secondary partition come from different primary partitions. We discuss one representative advantage: Wider than a regular convolution with the number of parameters and the computation complexity preserved. We also show that regular convolutions, group convolution with summation fusion, and the Xception block are special cases of interleaved group convolutions. Empirical results over standard benchmarks, CIFAR-10, CIFAR-100, SVHN and ImageNet demonstrate that our networks are more efficient in using parameters and computation complexity with similar or higher accuracy.
Publication Date
12-22-2017
Publication Title
Proceedings of the IEEE International Conference on Computer Vision
Volume
2017-October
Number of Pages
4383-4392
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICCV.2017.469
Copyright Status
Unknown
Socpus ID
85041905298 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85041905298
STARS Citation
Zhang, Ting; Qi, Guo Jun; Xiao, Bin; and Wang, Jingdong, "Interleaved Group Convolutions" (2017). Scopus Export 2015-2019. 7386.
https://stars.library.ucf.edu/scopus2015/7386