# Attention Round for Post-Training Quantization

arXiv: https://arxiv.org/abs/2207.03088 · HTML: https://mlsanity.com/paper/2207.03088/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 7 Jul 2022.

## Builds on (most cited first, 12 of 12)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [Deep Learning with Limited Numerical Precision](https://mlsanity.com/paper/1502.02551/) (2015)
- [Dynamic Network Surgery for Efficient DNNs](https://mlsanity.com/paper/1608.04493/) (2016)
- [Low-bit Quantization of Neural Networks for Efficient Inference](https://mlsanity.com/paper/1902.06822/) (2019)
- [Fixed Point Quantization of Deep Convolutional Networks](https://mlsanity.com/paper/1511.06393/) (2015)
- [Loss Aware Post-training Quantization](https://mlsanity.com/paper/1911.07190/) (2019)
- [NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm](https://mlsanity.com/paper/1711.02017/) (2017)
- [Any-Precision Deep Neural Networks](https://mlsanity.com/paper/1911.07346/) (2019)
- [Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning](https://mlsanity.com/paper/2004.11627/) (2020)
- [Fine-grained Data Distribution Alignment for Post-Training Quantization](https://mlsanity.com/paper/2109.04186/) (2021)

## Built on by (most cited first, 1 of 1)

- [A Selective Quantization Tuner for ONNX Models](https://mlsanity.com/paper/2507.12196/) (2025)

## Abstract (arXiv)

At present, the quantification methods of neural network models are mainly divided into post-training quantization (PTQ) and quantization aware training (QAT). Post-training quantization only need a small part of the data to complete the quantification process, but the performance of its quantitative model is not as good as the quantization aware training. This paper presents a novel quantification method called Attention Round. This method gives parameters w the opportunity to be mapped to all possible quantized values, rather than just the two quantized values nearby w in the process of quantization. The probability of being mapped to different quantified values is negatively correlated with the distance between the quantified values and w, and decay with a Gaussian function. In addition, this paper uses the lossy coding length as a measure to assign bit widths to the different layers of the model to solve the problem of mixed precision quantization, which effectively avoids to solve combinatorial optimization problem. This paper also performs quantitative experiments on different models, the results confirm the effectiveness of the proposed method. For ResNet18 and MobileNetV2, the post-training quantization proposed in this paper only require 1,024 training data and 10 minutes to complete the quantization process, which can achieve quantization performance on par with quantization aware training.