{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/shufflenet-an-extremely-efficient","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","arxiv_id":"1707.01083","date":"2017-07-04","proceeding":"CVPR 2018 6","authors":["Xiangyu Zhang","Xinyu Zhou","Mengxiao Lin","Jian Sun"],"abstract":"We introduce an extremely computation-efficient CNN architecture named\nShuffleNet, which is designed specially for mobile devices with very limited\ncomputing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new\noperations, pointwise group convolution and channel shuffle, to greatly reduce\ncomputation cost while maintaining accuracy. Experiments on ImageNet\nclassification and MS COCO object detection demonstrate the superior\nperformance of ShuffleNet over other structures, e.g. lower top-1 error\n(absolute 7.8%) than recent MobileNet on ImageNet classification task, under\nthe computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet\nachieves ~13x actual speedup over AlexNet while maintaining comparable\naccuracy.","url_abs":"http://arxiv.org/abs/1707.01083v2","url_pdf":"http://arxiv.org/pdf/1707.01083v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/0jason000/ShuffleNetV1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/Deci-AI/super-gradients","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/Mayurji/Image-Classification-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/MrRen-sdhm/Embedded_Multi_Object_Detection_CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/afzalahmad0203/Numpy-Shufflenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/afzalahmad0203/Tensorflow-Shufflenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/afzalahmad0203/tf_shufflenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/alalagong/LEDNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/bpuladi/Automated-PD-L1-Scoring","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/clavichord93/MENet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/deep-learning-algorithm/LightWeightCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/eogussla12/Shufflenet_CIFAR10_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/europa1610/Tensorflow-Shufflenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/marload/ConvNets-TensorFlow2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/mg2033/shufflenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/minhto2802/keras-shufflenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/tensorpack/tensorpack/tree/master/examples/ImageNetModels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/tropcomplique/shufflenet-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/zjZSTU/LightWeightCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/2023-MindSpore-1/ms-code-14","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/2023-MindSpore-1/ms-code-223/tree/main/ShuffleNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/2023-MindSpore-1/ms-code-38","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/2023-MindSpore-4/Code10/tree/main/SSD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/2023-MindSpore-4/Code10/tree/main/ShuffleNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/2023-MindSpore-4/Code9/tree/main/ShuffleNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/2024-MindSpore-1/Code4/tree/main/ShuffleNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/GordonnW/ShuffleNetV1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/shufflenet_v1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/ShuffleNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/marlcplhra/ShuffleNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/mindlab-ai/mindcv/blob/main/mindcv/models/shufflenetv1.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/mindspore-ai/models/blob/master/official/cv/shufflenetv1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/mindspore-ecosystem/mindcv/blob/main/mindcv/models/shufflenetv1.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/open-mmlab/mmclassification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/open-mmlab/mmpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://github.com/yangyucheng000/shufflenetv1/blob/main/shufflenetv1.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"shufflenet-an-extremely-efficient","repo_url":"https://gitlab.com/birder/birder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"channel-shuffle","method_name":"Channel Shuffle"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"shufflenet","method_name":"ShuffleNet"},{"method_slug":"shufflenet-block","method_name":"ShuffleNet Block"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"step-decay","method_name":"Step Decay"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"shufflenet","name":"ShuffleNet","full_name":"ShuffleNet"},{"slug":"shufflenet-block","name":"ShuffleNet Block","full_name":"ShuffleNet Block"}],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ShuffleNet","rank_in_archive_order":1017,"of":1060,"metrics":{"Top 1 Accuracy":"70.9%"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-dukemtmc-reid","task":"Person Re-Identification","dataset":"DukeMTMC-reID","model":"ShuffleNetV2 [zhang2018shufflenet]","rank_in_archive_order":83,"of":94,"metrics":{"mAP":"48.09"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.01083","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}