MobileNetV2: Inverted Residuals and Linear Bottlenecks

In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. We also describe efficient ways of applying these mobile models to object detectio...

Full description

Bibliographic Details

Published in:	2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 4510 - 4520
Main Authors:	Sandler, Mark, Howard, Andrew, Zhu, Menglong, Zhmoginov, Andrey, Chen, Liang-Chieh
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.06.2018
Subjects:	Computational modeling Computer architecture Manifolds Neural networks Task analysis
ISSN:	1063-6919
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!