Papers › Interleaved Group Convolutions for Deep Neural Networks

Interleaved Group Convolutions for Deep Neural Networks

10 Jul 2017arXiv:1707.02725archive 2025-07-28

Ting Zhang, Guo-Jun Qi, Bin Xiao, Jingdong Wang

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.

PaperPDFCode

Code

homles11/IGCV3 mentioned on GitHubtf report
xxradon/IGCV3-pytorch mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionGlobal Average PoolingMax PoolingPointwise ConvolutionReLUResidual ConnectionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections