• Computer Science
  • Published in ArXiv 2017

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

@article{Howard2017MobileNetsEC,
  title={MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications},
  author={Andrew G. Howard and Menglong Zhu and Bo Chen and Dmitry Kalenichenko and Weijun Wang and Tobias Weyand and Marco Andreetto and Hartwig Adam},
  journal={ArXiv},
  year={2017},
  volume={abs/1704.04861}
}
Highlight Information
We present a class of efficient models called MobileNets for mobile and embedded vision applications. [...] Key Method These hyper-parameters allow the model builder to choose the right sized model for their application based on the constraints of the problem. We present extensive experiments on resource and accuracy tradeoffs and show strong performance compared to other popular models on ImageNet classification. We then demonstrate the effectiveness of MobileNets across a wide range of applications and use…Expand Abstract

Citations

Publications citing this paper.
SHOWING 1-10 OF 2,829 CITATIONS

Depthwise Separable Convolutions for Neural Machine Translation

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Neural Architecture Search over Decentralized Data

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

On-Device Information Extraction from Screenshots in form of tags

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

2019-0401 Increased Cyclist Safety Using an Embedded System

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Channel Pruning Algorithm Based on Depth-Wise Separable Convolution Unit

VIEW 22 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Comprehensive Overhaul of Feature Distillation

VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A Fully Quantitative Scheme With Fine-grained Tuning Method For Lightweight CNN Acceleration

  • Chenguang Yang, Bowen Li, Yizhou Wang
  • Computer Science
  • 2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS)
  • 2019
VIEW 9 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A Hybrid Deep Learning Architecture for Leukemic B-lymphoblast Classification

VIEW 11 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A Muti-branch Convolutional Netural Network for Mobile Platform

VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

ADSCNet: asymmetric depthwise separable convolution for semantic segmentation in real-time

VIEW 15 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2020

CITATION STATISTICS

  • 808 Highly Influenced Citations

  • Averaged 896 Citations per year from 2017 through 2019

  • 76% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 37 REFERENCES

Distilling the Knowledge in a Neural Network

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Rethinking the Inception Architecture for Computer Vision

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Going deeper with convolutions

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Factorized Convolutional Neural Networks

VIEW 1 EXCERPT