mlsanityData to 7 Oct 2026

Make RepVGG Greater Again: A Quantization-aware Approach

arXiv 2212.01593 ↗First posted 3 Dec 2022cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

The tradeoff between performance and inference speed is critical for practical applications. Architecture reparameterization obtains better tradeoffs and it is becoming an increasingly popular ingredient in modern convolutional neural networks. Nonetheless, its quantization performance is usually too poor to deploy (more than 20% top-1 accuracy drop on ImageNet) when INT8 inference is desired. In this paper, we dive into the underlying mechanism of this failure, where the original design inevitably enlarges quantization error. We propose a simple, robust, and effective remedy to have a quantization-friendly structure that also enjoys reparameterization benefits. Our method greatly bridges the gap between INT8 and FP32 accuracy for RepVGG. Without bells and whistles, the top-1 accuracy drop on ImageNet is reduced within 2% by standard post-training quantization. Moreover, our method also achieves similar FP32 performance as RepVGG. Extensive experiments on detection and semantic segmentation tasks verify its generalization.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 41 of its 59 references that are in the map. First posted on arXiv 3 Dec 2022.

Builds on

41 of 59 references.

References · 41

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2017Mask R-CNNcited by 7,259
  8. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  9. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  10. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  11. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  12. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
29 more
  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  2. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2019Searching for MobileNetV3cited by 1,984
  7. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  8. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  9. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  10. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  11. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  12. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  13. 2015Deep Learning with Limited Numerical Precisioncited by 368
  14. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
  15. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  16. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 265
  17. 2020LSQ+: Improving low-bit quantization through learnable offsets and better initializationcited by 180
  18. 2019ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blockscited by 178
  19. 2018Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Searchcited by 122
  20. 2021Diverse Branch Block: Building a Convolution as an Inception-like Unitcited by 87
  21. 2022PP-YOLOE: An evolved version of YOLOcited by 75
  22. 2017DiracNets: Training Very Deep Neural Networks Without Skip-Connectionscited by 47
  23. 2022Re-parameterizing Your Optimizers rather than Architecturescited by 35
  24. 2018A Quantization-Friendly Separable Convolution for MobileNetscited by 22
  25. 2021BatchQuant: Quantized-for-all Architecture Search with Robust Quantizercited by 19
  26. 2022Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Reportcited by 16
  27. 2021Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamicscited by 12
  28. 2022DyRep: Bootstrapping Training with Dynamic Re-parameterizationcited by 11
  29. 2021HPTQ: Hardware-Friendly Post Training Quantizationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 8; 2025: 5; 2026: 1.

21 papers.

Sort:

By area:

  1. 2024MobileVLM V2: Faster and Stronger Baseline for Vision Language Modelcited by 172
  2. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
  3. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
  4. 2023MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devicescited by 120
  5. 2024LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detectioncited by 29
  6. 2023RepViT-SAM: Towards Real-Time Segmenting Anythingcited by 17
  7. 2025Low-bit Model Quantization for Deep Neural Networks: A Surveycited by 11
  8. 2023Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splittingcited by 6
  9. 2025Diffusion Model Quantization: A Reviewcited by 6
  10. 2024VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Datasetcited by 4
  11. 2024Towards Improved Semiconductor Defect Inspection for high-NA EUVL based on SEMI-SuperYOLO-NAScited by 2
  12. 2025D2-DPM: Dual Denoising for Quantized Diffusion Probabilistic Modelscited by 2
9 more
  1. 2024PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slicescited by 1
  2. 2025FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precisioncited by 1
  3. 2023RepQ: Generalizing Quantization-Aware Training for Re-Parametrized Architecturescited by 0
  4. 2023MaxQ: Multi-Axis Query for N:M Sparsity Networkcited by 0
  5. 2024Outlier-Aware Training for Low-Bit Quantization of Structural Re-Parameterized Networkscited by 0
  6. 2024Towards Accurate Post-training Quantization for Reparameterized Modelscited by 0
  7. 2024Small Object Detection for Indoor Assistance to the Blind using YOLO NAS Small and Super Gradientscited by 0
  8. 2025Q2: Quantization-Aware Gradient Balancing and Attention Alignment for Low-Bit Quantizationcited by 0
  9. 2026Exploring Reliable Spatiotemporal Dependencies for Efficient Visual Trackingcited by 0