Papers › MGIC: Multigrid-in-Channels Neural Network Architectures

MGIC: Multigrid-in-Channels Neural Network Architectures

17 Nov 2020NeurIPS Workshop DLDE 2021 12arXiv:2011.09128archive 2025-07-28

Moshe Eliasof, Jonathan Ephrath, Lars Ruthotto, Eran Treister

We present a multigrid-in-channels (MGIC) approach that tackles the quadratic growth of the number of parameters with respect to the number of channels in standard convolutional neural networks (CNNs). Thereby our approach addresses the redundancy in CNNs that is also exposed by the recent success of lightweight CNNs. Lightweight CNNs can achieve comparable accuracy to standard CNNs with fewer parameters; however, the number of weights still scales quadratically with the CNN's width. Our MGIC architectures replace each CNN block with an MGIC counterpart that utilizes a hierarchy of nested grouped convolutions of small group size to address this. Hence, our proposed architectures scale linearly with respect to the network's width while retaining full coupling of the channels as in standard CNNs. Our extensive experiments on image classification, segmentation, and point cloud classification show that applying this strategy to different architectures like ResNet and MobileNetV3 reduces the number of parameters while obtaining similar or better accuracy.

PaperPDFConference PDFCode

Code

bgucompsci/multigridinchannelscnns officialmentioned in paperpytorch 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.

Tasks

Image ClassificationPoint Cloud Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutGlobal Average PoolingHard SwishInverted Residual BlockKaiming InitializationMax PoolingPointwise ConvolutionReLUReLU6Residual BlockResidual ConnectionSigmoid ActivationSqueeze-and-Excitation Block

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