LINEAiGE
AI HISTORY

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto and Hartwig Adam submitted MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications on April 17, 2017. The paper presents MobileNets as efficient models for mobile and embedded vision applications, based on depthwise separable convolutions and two global hyperparameters for trading off latency and accuracy.

April 17, 2017AI HISTORYVERIFIED

Historical classification

This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.

Why it matters

A documented research milestone for the MobileNet model family and efficient on-device computer vision, recorded at the original paper-submission level rather than as an invention, development-start, software-release or universal-priority claim.

People, organizations & technologies

PEOPLE
Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam

TECHNOLOGIES
MobileNet, Depthwise separable convolution, On-device computer vision

Evidence & verification

STATE
verified

CONFIDENCE
high

LAST VERIFIED
2026-09-14T06:05:36+08:00

The original arXiv record supports the title, authors, April 17 2017 submission date and the paper's description of MobileNets as efficient models for mobile and embedded vision using depthwise separable convolutions and global width/resolution hyperparameters. Google Research's April 3 2018 MobileNetV2 announcement independently identifies MobileNetV1 as the prior generation and cites the 2017 MobileNets paper. The day-precision date is attached specifically to the arXiv submission milestone, not asserted as an invention, model-family birth, development-start, code release or universal priority date. No institutional affiliation, geography, ancestry, influence or causality is inferred.

Sources

SOURCE 1 · PRIMARY · CLAIM-EVIDENCE

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

arXiv

PUBLISHED
2017-04-17

SOURCE 2 · PRIMARY · CORROBORATION

MobileNetV2: The Next Generation of On-Device Computer Vision Networks

Google Research

PUBLISHED
2018-04-03

Trace the chronology

Record identity

LINEAiGE ID
mobilenet-paper-2017