# Quantization for Rapid Deployment of Deep Neural Networks

arXiv: https://arxiv.org/abs/1810.05488 · HTML: https://mlsanity.com/paper/1810.05488/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2018.

## Built on by (most cited first, 20 of 20)

- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [PD-Quant: Post-Training Quantization based on Prediction Difference Metric](https://mlsanity.com/paper/2212.07048/) (2022)
- [VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference](https://mlsanity.com/paper/2102.04503/) (2021)
- [Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI](https://mlsanity.com/paper/2111.06061/) (2021)
- [Post-training Quantization for Neural Networks with Provable Guarantees](https://mlsanity.com/paper/2201.11113/) (2022)
- [Applications and Techniques for Fast Machine Learning in Science](https://mlsanity.com/paper/2110.13041/) (2021)
- [Efficient Quantization Strategies for Latent Diffusion Models](https://mlsanity.com/paper/2312.05431/) (2023)
- [HPTQ: Hardware-Friendly Post Training Quantization](https://mlsanity.com/paper/2109.09113/) (2021)
- [Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review](https://mlsanity.com/paper/2311.11883/) (2023)
- [Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deployment](https://mlsanity.com/paper/2202.05048/) (2022)
- [Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT Systems](https://mlsanity.com/paper/2303.12557/) (2023)
- [DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization](https://mlsanity.com/paper/2507.12933/) (2025)
- [Rethinking Floating Point Overheads for Mixed Precision DNN Accelerators](https://mlsanity.com/paper/2101.11748/) (2021)
- [Symmetry Regularization and Saturating Nonlinearity for Robust Quantization](https://mlsanity.com/paper/2208.00338/) (2022)
- [On the Impact of Black-box Deployment Strategies for Edge AI on Latency and Model Performance](https://mlsanity.com/paper/2403.17154/) (2024)
- [QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices](https://mlsanity.com/paper/2407.02327/) (2024)
- [FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation](https://mlsanity.com/paper/2203.12091/) (2022)
- [Quantizing YOLOv7: A Comprehensive Study](https://mlsanity.com/paper/2407.04943/) (2024)
- [On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance](https://mlsanity.com/paper/2411.00907/) (2024)
- [EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices](https://mlsanity.com/paper/2506.11093/) (2025)

## Abstract (arXiv)

This paper aims at rapid deployment of the state-of-the-art deep neural networks (DNNs) to energy efficient accelerators without time-consuming fine tuning or the availability of the full datasets. Converting DNNs in full precision to limited precision is essential in taking advantage of the accelerators with reduced memory footprint and computation power. However, such a task is not trivial since it often requires the full training and validation datasets for profiling the network statistics and fine tuning the networks to recover the accuracy lost after quantization. To address these issues, we propose a simple method recognizing channel-level distribution to reduce the quantization-induced accuracy loss and minimize the required image samples for profiling. We evaluated our method on eleven networks trained on the ImageNet classification benchmark and a network trained on the Pascal VOC object detection benchmark. The results prove that the networks can be quantized into 8-bit integer precision without fine tuning.