mlsanityData to 7 Oct 2026

RepVGG: Making VGG-style ConvNets Great Again

arXiv 2101.03697 ↗First posted 11 Jan 2021cs.CV cs.AI cs.LGcited by 520

Not on the map. Why?

Abstract (arXiv)

We present a simple but powerful architecture of convolutional neural network, which has a VGG-like inference-time body composed of nothing but a stack of 3x3 convolution and ReLU, while the training-time model has a multi-branch topology. Such decoupling of the training-time and inference-time architecture is realized by a structural re-parameterization technique so that the model is named RepVGG. On ImageNet, RepVGG reaches over 80% top-1 accuracy, which is the first time for a plain model, to the best of our knowledge. On NVIDIA 1080Ti GPU, RepVGG models run 83% faster than ResNet-50 or 101% faster than ResNet-101 with higher accuracy and show favorable accuracy-speed trade-off compared to the state-of-the-art models like EfficientNet and RegNet. The code and trained models are available at https://github.com/megvii-model/RepVGG.

Key facts. Cited by 520 papers in the map (data through 7 Oct 2026). Builds on 36 of its 46 references that are in the map. First posted on arXiv 11 Jan 2021.

Builds on

36 of 46 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  9. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  10. 2014Going Deeper with Convolutionscited by 4,231
  11. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  12. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
24 more
  1. 2016Pyramid Scene Parsing Networkcited by 2,472
  2. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  3. 2019Searching for MobileNetV3cited by 1,984
  4. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  5. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  6. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  7. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  8. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  9. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  10. 2020Designing Network Design Spacescited by 954
  11. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  12. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  13. 2017Progressive Neural Architecture Searchcited by 483
  14. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  15. 2014cuDNN: Efficient Primitives for Deep Learningcited by 240
  16. 2019ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blockscited by 178
  17. 2018Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networkscited by 176
  18. 2015Fast Algorithms for Convolutional Neural Networkscited by 102
  19. 2019Centripetal SGD for Pruning Very Deep Convolutional Networks with Complicated Structurecited by 76
  20. 2018ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networkscited by 53
  21. 2017DiracNets: Training Very Deep Neural Networks Without Skip-Connectionscited by 47
  22. 2019Approximated Oracle Filter Pruning for Destructive CNN Width Optimizationcited by 35
  23. 2020DO-Conv: Depthwise Over-parameterized Convolutional Layercited by 28
  24. 2018RePr: Improved Training of Convolutional Filterscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 34; 2022: 92; 2023: 126; 2024: 139; 2025: 80; 2026: 49.

520 papers.

Sort:

By area:

  1. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  2. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  3. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  4. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  5. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 498
  6. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  7. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 292
  8. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  9. 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 200
  10. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  11. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 161
  12. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
38 more
  1. 2023Stabilizing Transformer Training by Preventing Attention Entropy Collapsecited by 154
  2. 2023GSVA: Generalized Segmentation via Multimodal Large Language Modelscited by 153
  3. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
  4. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
  5. 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speedcited by 119
  6. 2022Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learningcited by 118
  7. 2022MobileOne: An Improved One millisecond Mobile Backbonecited by 109
  8. 2024Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chipscited by 97
  9. 2023MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Trainingcited by 96
  10. 20223D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentationcited by 94
  11. 2022Three things everyone should know about Vision Transformerscited by 90
  12. 2021Diverse Branch Block: Building a Convolution as an Inception-like Unitcited by 87
  13. 2022What Makes Convolutional Models Great on Long Sequence Modeling?cited by 86
  14. 2023InceptionNeXt: When Inception Meets ConvNeXtcited by 84
  15. 2023One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuningcited by 84
  16. 2022Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognitioncited by 81
  17. 2021RobustART: Benchmarking Robustness on Architecture Design and Training Techniquescited by 78
  18. 2022PP-YOLOE: An evolved version of YOLOcited by 75
  19. 2023Towards Efficient Visual Adaption via Structural Re-parameterizationcited by 73
  20. 2022Representation Compensation Networks for Continual Semantic Segmentationcited by 72
  21. 2022A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shiftcited by 68
  22. 2023UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognitioncited by 64
  23. 20226D Rotation Representation For Unconstrained Head Pose Estimationcited by 63
  24. 2022Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Featurescited by 63
  25. 2023ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptationcited by 58
  26. 2024Multi-Task Dense Prediction via Mixture of Low-Rank Expertscited by 58
  27. 2024The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Reportcited by 57
  28. 2022CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Drivingcited by 56
  29. 2023Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolutioncited by 56
  30. 2024SHViT: Single-Head Vision Transformer with Memory Efficient Macro Designcited by 55
  31. 2022Residual Local Feature Network for Efficient Super-Resolutioncited by 53
  32. 2024UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentationcited by 53
  33. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  34. 2022The Lie Derivative for Measuring Learned Equivariancecited by 51
  35. 2024FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localizationcited by 51
  36. 2024U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformerscited by 51
  37. 2021DANets: Deep Abstract Networks for Tabular Data Classification and Regressioncited by 50
  38. 2021FaceX-Zoo: A PyTorch Toolbox for Face Recognitioncited by 49

50 most cited of 520 All 520 (JSON)