ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

Abstract

Currently, the neural network architecture design is mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, e.g., speed, also depends on the other factors such as memory access cost and platform characterics. Thus, this work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs. Based on a series of controlled experiments, this work derives several practical guidelines for efficient network design. Accordingly, a new architecture is presented, called ShuffleNet V2. Comprehensive ablation experiments verify that our model is the state-of-the-art in terms of speed and accuracy tradeoff.

Keywords

Computer scienceFLOPSMetric (unit)ArchitectureComputationPerformance metricComputer engineeringDistributed computingComputer architectureParallel computingAlgorithm

Affiliated Institutions

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 2018 IEEE/CVF Conference on Computer ... 8394 citations

ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

Qilong Wang , Banggu Wu , Pengfei Zhu +3 more

Recently, channel attention mechanism has demonstrated to offer great potential in improving the performance of deep convolutional neural networks (CNNs). However, most existing...

2020 2020 IEEE/CVF Conference on Computer ... 6942 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

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

Wenhai Wang , Enze Xie , Xiang Li +6 more

Although convolutional neural networks (CNNs) have achieved great success in computer vision, this work investigates a simpler, convolution-free backbone network use-fid for man...

2021 2021 IEEE/CVF International Conferenc... 4221 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

Publication Info

Year: 2018
Type: book-chapter
Pages: 122-138
Citations: 6005
Access: Closed

External Links

Download PDF (Free) View on DOI.org arXiv PubMed Semantic Scholar

Social Impact

Altmetric

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

6005

OpenAlex

611

Influential

Cite This

APA Style

                            
                                    Ningning Ma, 
                                
                                    Xiangyu Zhang, 
                                
                                    Hai-Tao Zheng
                                
                                et al.
                            
                            (2018). 
                            ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design. 
                            Lecture notes in computer science
                            
                            , 122-138.
                            https://doi.org/10.1007/978-3-030-01264-9_8

Identifiers

DOI: 10.1007/978-3-030-01264-9_8
PMID: 41328267
PMCID: PMC12664865
arXiv: 1807.11164

Data Quality

Data completeness: 79%