# Quantized Convolutional Neural Networks for Mobile Devices

arXiv: https://arxiv.org/abs/1512.06473 · HTML: https://mlsanity.com/paper/1512.06473/

## Key facts

- Cited by 215 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2015.

## Built on by (most cited first, 30 of 215)

- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [SqueezeLLM: Dense-and-Sparse Quantization](https://mlsanity.com/paper/2306.07629/) (2023)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [I-BERT: Integer-only BERT Quantization](https://mlsanity.com/paper/2101.01321/) (2021)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [Cross-Image Relational Knowledge Distillation for Semantic Segmentation](https://mlsanity.com/paper/2204.06986/) (2022)
- [Distilling Object Detectors via Decoupled Features](https://mlsanity.com/paper/2103.14475/) (2021)
- [DataDAM: Efficient Dataset Distillation with Attention Matching](https://mlsanity.com/paper/2310.00093/) (2023)
- [GPTVQ: The Blessing of Dimensionality for LLM Quantization](https://mlsanity.com/paper/2402.15319/) (2024)
- [VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference](https://mlsanity.com/paper/2102.04503/) (2021)
- [hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices](https://mlsanity.com/paper/2103.05579/) (2021)
- [Pufferfish: Communication-efficient Models At No Extra Cost](https://mlsanity.com/paper/2103.03936/) (2021)
- [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021)
- [Online Continual Learning for Embedded Devices](https://mlsanity.com/paper/2203.10681/) (2022)
- [Hessian-Aware Pruning and Optimal Neural Implant](https://mlsanity.com/paper/2101.08940/) (2021)
- [Zero-shot Adversarial Quantization](https://mlsanity.com/paper/2103.15263/) (2021)
- [Combined Depth Space based Architecture Search For Person Re-identification](https://mlsanity.com/paper/2104.04163/) (2021)
- [Manifold Regularized Dynamic Network Pruning](https://mlsanity.com/paper/2103.05861/) (2021)
- [Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations](https://mlsanity.com/paper/2205.13571/) (2022)
- [Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition](https://mlsanity.com/paper/2107.11442/) (2021)
- [A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation](https://mlsanity.com/paper/2307.12574/) (2023)
- [Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications](https://mlsanity.com/paper/2204.11786/) (2022)
- [Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference](https://mlsanity.com/paper/2102.11289/) (2021)
- [Smart at what cost? Characterising Mobile Deep Neural Networks in the wild](https://mlsanity.com/paper/2109.13963/) (2021)
- [Cuttlefish: Low-Rank Model Training without All the Tuning](https://mlsanity.com/paper/2305.02538/) (2023)
- [BiBench: Benchmarking and Analyzing Network Binarization](https://mlsanity.com/paper/2301.11233/) (2023)
- [EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge](https://mlsanity.com/paper/2311.10986/) (2023)
- [Learned Gradient Compression for Distributed Deep Learning](https://mlsanity.com/paper/2103.08870/) (2021)
- [PowerQuant: Automorphism Search for Non-Uniform Quantization](https://mlsanity.com/paper/2301.09858/) (2023)
- [OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization](https://mlsanity.com/paper/2205.11141/) (2022)

## Abstract (arXiv)

Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks. However, high performance hardware is typically indispensable for the application of CNN models due to the high computation complexity, which prohibits their further extensions. In this paper, we propose an efficient framework, namely Quantized CNN, to simultaneously speed-up the computation and reduce the storage and memory overhead of CNN models. Both filter kernels in convolutional layers and weighting matrices in fully-connected layers are quantized, aiming at minimizing the estimation error of each layer's response. Extensive experiments on the ILSVRC-12 benchmark demonstrate 4~6x speed-up and 15~20x compression with merely one percentage loss of classification accuracy. With our quantized CNN model, even mobile devices can accurately classify images within one second.