前言

introduction的目的：讓初看這篇文章的人了解背景知識與問題。

從introduction 看 U-net

In the last two years, deep convolutional networks have outperformed the state of the art in many visual recognition tasks, e.g. [7,3]. While convolutional networks have already existed for a long time [8], their success was limited due to the size of the available training sets and the size of the considered networks. The breakthrough by Krizhevsky et al. [7] was due to supervised training of a large network with 8 layers and millions of parameters on the ImageNet dataset with 1 million training images. Since then, even larger and deeper networks have been trained [12].

首先，介紹了一個技術 "convolutional networks"。

[7] Alexnet，學習CNN一定要知道的network
[3] R-CNN，利用CNN解決物件偵測問題的第一人
[8] 古老的CNN
[12] VGGNet，用大型的network去辨識問題

convolutional networks

就是俗稱的CNN

ImageNet

一個非常大的標註資料數據集。

結語

U-net之前，已經發展了許多CNN技術，明天我們從U-net的架構，來剖析一下CNN有哪些發展吧~~

參考文獻

上古時期的CNN
Alexnet
R-CNN
VGGNet