mlsanityData to 7 Oct 2026

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

arXiv 1707.01083 ↗First posted 4 Jul 2017cs.CVcited by 1,194

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1,194 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 295; 2022: 249; 2023: 226; 2024: 183; 2025: 170; 2026: 71.

1,194 papers.

Sort:

By area:

  1. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  2. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  3. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  4. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
  5. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
  6. 2021Distilling Knowledge via Knowledge Reviewcited by 285
  7. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
  8. 2021HINet: Half Instance Normalization Network for Image Restorationcited by 236
  9. 2021Mobile-Former: Bridging MobileNet and Transformercited by 234
  10. 2022TinyViT: Fast Pretraining Distillation for Small Vision Transformerscited by 232
  11. 2021AdaViT: Adaptive Vision Transformers for Efficient Image Recognitioncited by 228
  12. 2021A Geometric Analysis of Neural Collapse with Unconstrained Featurescited by 226
38 more
  1. 2021Co-Scale Conv-Attentional Image Transformerscited by 224
  2. 2021WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognitioncited by 221
  3. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  4. 2022Visual Attention Networkcited by 210
  5. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  6. 2022Knowledge Distillation from A Stronger Teachercited by 204
  7. 2022Focal Modulation Networkscited by 186
  8. 2023EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attentioncited by 172
  9. 2022Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communicationscited by 166
  10. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 161
  11. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  12. 2023Neural Video Compression with Diverse Contextscited by 155
  13. 2021Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognitioncited by 143
  14. 2022Knowledge Distillation with the Reused Teacher Classifiercited by 140
  15. 2021CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attentioncited by 139
  16. 2023Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networkscited by 129
  17. 2023Dataset Distillation: A Comprehensive Reviewcited by 126
  18. 2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124
  19. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
  20. 2022EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applicationscited by 121
  21. 2022Cross-Image Relational Knowledge Distillation for Semantic Segmentationcited by 117
  22. 2021Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspectivecited by 116
  23. 2022EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformerscited by 116
  24. 2021Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformercited by 115
  25. 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
  26. 2022Curriculum Temperature for Knowledge Distillationcited by 110
  27. 2022MobileOne: An Improved One millisecond Mobile Backbonecited by 109
  28. 2021On the Adversarial Robustness of Vision Transformerscited by 104
  29. 2024Logit Standardization in Knowledge Distillationcited by 101
  30. 2024MobileNetV4 -- Universal Models for the Mobile Ecosystemcited by 98
  31. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
  32. 2022Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shiftcited by 94
  33. 2021CAT: Cross Attention in Vision Transformercited by 92
  34. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  35. 2022Clifford Neural Layers for PDE Modelingcited by 91
  36. 2023DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attentioncited by 90
  37. 2023Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarkscited by 90
  38. 2021Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenescited by 89

50 most cited of 1,194 All 1,194 (JSON)