# Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deployment

arXiv: https://arxiv.org/abs/2202.05048 · HTML: https://mlsanity.com/paper/2202.05048/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 45 references that are in the map.
- First posted on arXiv 10 Feb 2022.

## Builds on (most cited first, 27 of 27)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [Variational Continual Learning](https://mlsanity.com/paper/1710.10628/) (2017)
- [Data-Free Quantization Through Weight Equalization and Bias Correction](https://mlsanity.com/paper/1906.04721/) (2019)
- [LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks](https://mlsanity.com/paper/1807.10029/) (2018)
- [MLPerf Inference Benchmark](https://mlsanity.com/paper/1911.02549/) (2019)
- [Low-bit Quantization of Neural Networks for Efficient Inference](https://mlsanity.com/paper/1902.06822/) (2019)
- [Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation](https://mlsanity.com/paper/2004.09602/) (2020)
- [Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss](https://mlsanity.com/paper/1808.05779/) (2018)
- [FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions](https://mlsanity.com/paper/2004.05565/) (2020)
- [Improving Neural Network Quantization without Retraining using Outlier Channel Splitting](https://mlsanity.com/paper/1901.09504/) (2019)
- [Fixed Point Quantization of Deep Convolutional Networks](https://mlsanity.com/paper/1511.06393/) (2015)
- [Glow: Graph Lowering Compiler Techniques for Neural Networks](https://mlsanity.com/paper/1805.00907/) (2018)
- [TVM: An Automated End-to-End Optimizing Compiler for Deep Learning](https://mlsanity.com/paper/1802.04799/) (2018)
- [Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization](https://mlsanity.com/paper/1902.01917/) (2019)
- [Intel nGraph: An Intermediate Representation, Compiler, and Executor for Deep Learning](https://mlsanity.com/paper/1801.08058/) (2018)
- [Quantization for Rapid Deployment of Deep Neural Networks](https://mlsanity.com/paper/1810.05488/) (2018)
- [Efficient Execution of Quantized Deep Learning Models: A Compiler Approach](https://mlsanity.com/paper/2006.10226/) (2020)
- [Fixed-point optimization of deep neural networks with adaptive step size retraining](https://mlsanity.com/paper/1702.08171/) (2017)
- [Fast Adjustable Threshold For Uniform Neural Network Quantization (Winning solution of LPIRC-II)](https://mlsanity.com/paper/1812.07872/) (2018)
- [Automated Backend-Aware Post-Training Quantization](https://mlsanity.com/paper/2103.14949/) (2021)

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

- [QuantuneV2: Compiler-Based Local Metric-Driven Mixed Precision Quantization for Practical Embedded AI Applications](https://mlsanity.com/paper/2501.07161/) (2025)
- [Edge AI for Internet of Energy: Challenges and Perspectives](https://mlsanity.com/paper/2311.16851/) (2023)
- [NITRO-D: Native Integer-only Training of Deep Convolutional Neural Networks](https://mlsanity.com/paper/2407.11698/) (2024)
- [Mixed-Precision Training and Compilation for RRAM-based Computing-in-Memory Accelerators](https://mlsanity.com/paper/2601.21737/) (2026)
- [ALADIN: Accuracy-Latency-Aware Design-space Inference Analysis for Embedded AI Accelerators](https://mlsanity.com/paper/2603.08722/) (2026)
- [Compact convolutional neural networks for AI-based drone detection system](https://mlsanity.com/paper/2607.16455/) (2026)

## Abstract (arXiv)

To adopt convolutional neural networks (CNN) for a range of resource-constrained targets, it is necessary to compress the CNN models by performing quantization, whereby precision representation is converted to a lower bit representation. To overcome problems such as sensitivity of the training dataset, high computational requirements, and large time consumption, post-training quantization methods that do not require retraining have been proposed. In addition, to compensate for the accuracy drop without retraining, previous studies on post-training quantization have proposed several complementary methods: calibration, schemes, clipping, granularity, and mixed-precision. To generate a quantized model with minimal error, it is necessary to study all possible combinations of the methods because each of them is complementary and the CNN models have different characteristics. However, an exhaustive or a heuristic search is either too time-consuming or suboptimal. To overcome this challenge, we propose an auto-tuner known as Quantune, which builds a gradient tree boosting model to accelerate the search for the configurations of quantization and reduce the quantization error. We evaluate and compare Quantune with the random, grid, and genetic algorithms. The experimental results show that Quantune reduces the search time for quantization by approximately 36.5x with an accuracy loss of 0.07 ~ 0.65% across six CNN models, including the fragile ones (MobileNet, SqueezeNet, and ShuffleNet). To support multiple targets and adopt continuously evolving quantization works, Quantune is implemented on a full-fledged compiler for deep learning as an open-sourced project.