mlsanityData to 7 Oct 2026

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

arXiv 1807.11164 ↗First posted 30 Jul 2018cs.CVcited by 1,132

Not on the map. Why?

Abstract (arXiv)

Currently, the neural network architecture design is mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, e.g., speed, also depends on the other factors such as memory access cost and platform characterics. Thus, this work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs. Based on a series of controlled experiments, this work derives several practical guidelines for efficient network design. Accordingly, a new architecture is presented, called ShuffleNet V2. Comprehensive ablation experiments verify that our model is the state-of-the-art in terms of speed and accuracy tradeoff.

Key facts. Cited by 1,132 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 261; 2022: 231; 2023: 208; 2024: 195; 2025: 138; 2026: 98.

1,132 papers.

Sort:

By area:

  1. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  2. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  3. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  4. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636
  5. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  6. 2022Decoupled Knowledge Distillationcited by 380
  7. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  8. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  9. 2021Distilling Knowledge via Knowledge Reviewcited by 285
  10. 2022Vision Transformers for Single Image Dehazingcited by 255
  11. 2021I-BERT: Integer-only BERT Quantizationcited by 250
  12. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
38 more
  1. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 240
  2. 2021Coordinate Attention for Efficient Mobile Network Designcited by 239
  3. 2021HINet: Half Instance Normalization Network for Image Restorationcited by 236
  4. 2021Mobile-Former: Bridging MobileNet and Transformercited by 234
  5. 2021AdaViT: Adaptive Vision Transformers for Efficient Image Recognitioncited by 228
  6. 2021Parametric Contrastive Learningcited by 217
  7. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
  8. 2021Accelerating Sparse Deep Neural Networkscited by 213
  9. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  10. 2023EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attentioncited by 172
  11. 2021Pixel Difference Networks for Efficient Edge Detectioncited by 167
  12. 2022Separable Self-attention for Mobile Vision Transformerscited by 163
  13. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 161
  14. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  15. 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mambacited by 146
  16. 2021Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognitioncited by 143
  17. 2024MambaOut: Do We Really Need Mamba for Vision?cited by 142
  18. 2022Knowledge Distillation with the Reused Teacher Classifiercited by 140
  19. 2023Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networkscited by 129
  20. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
  21. 2021MPViT: Multi-Path Vision Transformer for Dense Predictioncited by 122
  22. 2022EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applicationscited by 121
  23. 2022EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformerscited by 116
  24. 2021VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistencycited by 114
  25. 2022Curriculum Temperature for Knowledge Distillationcited by 110
  26. 2021Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformerscited by 109
  27. 2022MobileOne: An Improved One millisecond Mobile Backbonecited by 109
  28. 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 108
  29. 2021Involution: Inverting the Inherence of Convolution for Visual Recognitioncited by 99
  30. 2021The Efficiency Misnomercited by 98
  31. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
  32. 2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
  33. 2022Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shiftcited by 94
  34. 2021CAT: Cross Attention in Vision Transformercited by 92
  35. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  36. 2023Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarkscited by 90
  37. 2023Rethinking Model Ensemble in Transfer-based Adversarial Attackscited by 88
  38. 2021Characterizing signal propagation to close the performance gap in unnormalized ResNetscited by 87

50 most cited of 1,132 All 1,132 (JSON)