MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, Howard, Zhu, Chen, Kalenichenko, Wang, Weyand, Andreetto, Adam; 2017 - Summary
author: zhaoyue-zephyrus
score: 10 / 10

The core idea of MobileNet is to use depthwise separable convolution to achieve better FLOPs-accuracy tradeoff compared to standard convolution.

Each depthwise separable convolution is a 3x3-depthwise convolution + BatchNorm + ReLU plus a 1x1 pointwise convolution + Batch + ReLU.

layer Standard Conv Depthwise Conv Pointwise (1x1-) Conv
Figure standard depth point
#Param \(K^2C_{in}C_{out}\) \(K^2C_{in}\) \(C_{in}C_{out}\)
computation cost \(K^2C_{in}C_{out}HW\) \(K^2C_{in}HW\) \(C_{in}C_{out}HW\)
(+ width multiplier) \(K^2(\alpha C_{in})(\alpha C_{out})HW\) \(K^2(\alpha C_{in})HW\) \((\alpha C_{in})(\alpha C_{out})HW\)
(+ res. multiplier ) \(K^2\alpha^2C_{in}C_{out}\rho^2HW\) \(K^2(\alpha C_{in})\rho^2HW\) \(\alpha^2C_{in}C_{out}\rho^2HW\)

(figure source:

The reduction is therefore \(\frac{1}{C_{out}} + \frac{1}{K^2}\).

(typical value: \(K=3, C_{in}\in\{32,...,512\}, C_{out}\in\{64,...,1024\}, \alpha\in\{0.25, 0.5, 0.75 \}, \rho\in\{\frac{192}{224},\frac{160}{224},\frac{128}{224} \}\))

In addition, MobileNet introduces two global hyperparameter to shrink model:

The paper conducts extensive studies on various computer vision tasks (ImageNet classification, fine-grained recognition, geo-localization, objection detection, etc.). On ImageNet, e.g., a MobileNet with \(\alpha=0.5\) and input size of 160 (i.e., \(\rho = 0.714\)) is 4% better than AlexNet while being 45x smaller and requiring 9.4x less FLOPs.