Papers › ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

4 Jul 2017CVPR 2018 6arXiv:1707.01083archive 2025-07-28

Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun

We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly reduce computation cost while maintaining accuracy. Experiments on ImageNet classification and MS COCO object detection demonstrate the superior performance of ShuffleNet over other structures, e.g. lower top-1 error (absolute 7.8%) than recent MobileNet on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves ~13x actual speedup over AlexNet while maintaining comparable accuracy.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

38 repositories listed; official and paper-mentioned ones first.

0jason000/ShuffleNetV1 mentioned on GitHubmindspore report
Deci-AI/super-gradients mentioned on GitHubpytorch report
Mayurji/Image-Classification-PyTorch mentioned on GitHubpytorch report
afzalahmad0203/tf_shufflenet mentioned on GitHubtf report
alalagong/LEDNet mentioned on GitHubpytorch report
clavichord93/MENet mentioned on GitHubpytorch report
deep-learning-algorithm/LightWeightCNN mentioned on GitHubpytorch report
eogussla12/Shufflenet_CIFAR10_Pytorch mentioned on GitHubpytorch report
marload/ConvNets-TensorFlow2 mentioned on GitHubtf report
mg2033/shufflenet mentioned on GitHubtf report
minhto2802/keras-shufflenet mentioned on GitHub report
osmr/imgclsmob mentioned on GitHubmxnetMIT report
tensorpack/tensorpack mentioned on GitHubtf report
zjZSTU/LightWeightCNN mentioned on GitHubpytorchApache-2.0 report
open-mmlab/mmpose pytorchApache-2.0 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

General ClassificationImage ClassificationObject DetectionPerson Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet ShuffleNet Top 1 Accuracy 70.9% #1017 of 1060 Archive leaderboard report
Person Re-Identification DukeMTMC-reID ShuffleNetV2 [zhang2018shufflenet] mAP 48.09 #83 of 94 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: ShuffleNet, ShuffleNet Block

1x1 ConvolutionAverage PoolingBatch NormalizationChannel ShuffleConvolutionDense ConnectionsDepthwise ConvolutionDropoutFaster R-CNNGlobal Average PoolingGrouped ConvolutionLocal Response NormalizationMax PoolingPointwise ConvolutionRPNRandom Horizontal FlipRandom Resized CropReLUResidual ConnectionRoIPoolShuffleNetShuffleNet BlockSoftmaxStep DecayWeight Decay

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