MobileNetV2: Inverted Residuals and Linear Bottlenecks

Mark SandlerAndrew HowardMenglong ZhuAndrey ZhmoginovLiang-Chieh Chen

   Papers with code   Abstract  PDF

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 detection in a novel framework we call SSDLite... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD
1
MobileNetV2 x1.0
73.0%
--
2
MobileNetV2
71.4%
72.0%
3
MobileNetV2 x0.75
69.8%
--
4
MobileNetV2 x0.5
64.0%
--
5
MobileNetV2 x0.25
51.7%
--