# Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting

arXiv: https://arxiv.org/abs/2312.10588 · HTML: https://mlsanity.com/paper/2312.10588/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 17 Dec 2023.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications](https://mlsanity.com/paper/2209.02976/) (2022)
- [Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation](https://mlsanity.com/paper/2004.09602/) (2020)
- [Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs](https://mlsanity.com/paper/2203.06717/) (2022)
- [Bayesian Bits: Unifying Quantization and Pruning](https://mlsanity.com/paper/2005.07093/) (2020)
- [ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting](https://mlsanity.com/paper/2007.03260/) (2020)
- [Robust Quantization: One Model to Rule Them All](https://mlsanity.com/paper/2002.07686/) (2020)
- [EasyQuant: Post-training Quantization via Scale Optimization](https://mlsanity.com/paper/2006.16669/) (2020)
- [Re-parameterizing Your Optimizers rather than Architectures](https://mlsanity.com/paper/2205.15242/) (2022)
- [RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality](https://mlsanity.com/paper/2112.11081/) (2021)
- [A Practical Mixed Precision Algorithm for Post-Training Quantization](https://mlsanity.com/paper/2302.05397/) (2023)
- [Make RepVGG Greater Again: A Quantization-aware Approach](https://mlsanity.com/paper/2212.01593/) (2022)
- [RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization](https://mlsanity.com/paper/2205.05671/) (2022)

## Built on by (most cited first, 6 of 6)

- [VAEVQ: Enhancing Discrete Visual Tokenization through Variational Modeling](https://mlsanity.com/paper/2511.06863/) (2025)
- [RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization](https://mlsanity.com/paper/2505.03803/) (2025)
- [FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2502.15488/) (2025)
- [OTARo: Once Tuning for All Precisions toward Robust On-Device LLMs](https://mlsanity.com/paper/2511.13147/) (2025)
- [Gradual Binary Search and Dimension Expansion : A general method for activation quantization in LLMs](https://mlsanity.com/paper/2504.13989/) (2025)
- [FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2511.09347/) (2025)

## Abstract (arXiv)

Although neural networks have made remarkable advancements in various applications, they require substantial computational and memory resources. Network quantization is a powerful technique to compress neural networks, allowing for more efficient and scalable AI deployments. Recently, Re-parameterization has emerged as a promising technique to enhance model performance while simultaneously alleviating the computational burden in various computer vision tasks. However, the accuracy drops significantly when applying quantization on the re-parameterized networks. We identify that the primary challenge arises from the large variation in weight distribution across the original branches. To address this issue, we propose a coarse & fine weight splitting (CFWS) method to reduce quantization error of weight, and develop an improved KL metric to determine optimal quantization scales for activation. To the best of our knowledge, our approach is the first work that enables post-training quantization applicable on re-parameterized networks. For example, the quantized RepVGG-A1 model exhibits a mere 0.3% accuracy loss. The code is in https://github.com/NeonHo/Coarse-Fine-Weight-Split.git