个人理解

创新点：
为什么：
怎么做：

一、摘要

  *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 effificient ways of applying these mobile models to object detection in a novel framework we call SSDLite. Additionally, we demonstrate how to build mobile semantic segmentation models through a reduced form of DeepLabv3 which we call Mobile DeepLabv3.* 

*It is based on an inverted residual structure where the shortcut connections are between the thin bottle neck layers. The intermediate expansion layer uses lightweight depthwise convolutions to fifilter features as a source of non-linearity. Additionally, we fifind that it is important to remove non-linearities in the narrow layers in order to maintain representational power. We demon strate that this improves performance and provide an in tuition that led to this design.*

Finally, our approach allows decoupling of the input/output domains from the expressiveness of the transformation, which provides a convenient framework for further analysis. We measure our performance on ImageNet classifification, COCO object detection, VOC image segmentation. We evaluate the trade-offs between accuracy, and number of operations measured by multiply-adds (MAdd), as well as actual latency, and the number of parameters.

提出了一个针对移动端的轻量级的卷积神经网络（MobileNet V2），该网络在许多计算机视觉任务上都达到很好的性能。