Quantized Convolutional Neural Networks for Mobile Devices

Abstract

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 ~ 6× speed-up and 15 ~ 20× compression with merely one percentage loss of classification accuracy. With our quantized CNN model, even mobile devices can accurately classify images within one second.

Keywords

Computer scienceConvolutional neural networkComputationBenchmark (surveying)Overhead (engineering)WeightingMobile deviceConvolutional codeArtificial intelligenceSpeedupPattern recognition (psychology)Computer engineeringAlgorithmParallel computingDecoding methods

Affiliated Institutions

Chinese Academy of Sciences CN

Related Publications

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

Xiangyu Zhang , Xinyu Zhou , Mengxiao Lin +1 more

We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150...

2018 8394 citations

GhostNet: More Features From Cheap Operations

Kai Han , Yunhe Wang , Qi Tian +3 more

Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources. The redundancy in feature maps is an importa...

2020 3894 citations

Rethinking the Inception Architecture for Computer Vision

Christian Szegedy , Vincent Vanhoucke , Sergey Ioffe +2 more

Convolutional networks are at the core of most state of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to bec...

2016 29577 citations

UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation

Zongwei Zhou , Md Mahfuzur Rahman Siddiquee , Nima Tajbakhsh +1 more

The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations...

2019 IEEE Transactions on Medical Imaging 3567 citations

Residual Dense Network for Image Super-Resolution

Yulun Zhang , Yapeng Tian , Yu Kong +2 more

A very deep convolutional neural network (CNN) has recently achieved great success for image super-resolution (SR) and offered hierarchical features as well. However, most deep ...

2018 3866 citations

Publication Info

Year: 2016
Type: preprint
Pages: 4820-4828
Citations: 1228
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Quantized Convolutional Neural Networks for Mobile Devices

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1228

OpenAlex

Cite This

APA Style

                            
                                    Jiaxiang Wu, 
                                
                                    Cong Leng, 
                                
                                    Yuhang Wang
                                
                                et al.
                            
                            (2016). 
                            Quantized Convolutional Neural Networks for Mobile Devices. 
                            
                            , 4820-4828.
                            https://doi.org/10.1109/cvpr.2016.521

Identifiers

DOI: 10.1109/cvpr.2016.521