前言

看Paper就是先看摘要。

從摘要看待U-net

There is large consent that successful training of deep networks requires many thousand annotated training samples.

說明困難: 一般的 deep learning 要上千張的照片。所以沒有超過一千張別玩深度學習了。

In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently.

做了什麼: 提出network與data augmentation策略增加標註資料的利用效率。

The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization.

實作: 一種特殊的架構。

We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

優勢: end-to-end, 很少圖片, 比2015年那時的方法好。

Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU.
優勢: 在GPU上很快, 比賽中最好。

The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net

實作: 實作在這裡。

不同角度看待U-net

有沒有發現...作者介紹的U-net好像跟我們在網路上Google的U-net有點不一樣。

維基百科

U-Net is a convolutional neural network that was developed for biomedical image segmentation at the Computer Science Department of the University of Freiburg, Germany.[1] The network is based on the fully convolutional network[2] and its architecture was modified and extended to work with fewer training images and to yield more precise segmentations. Segmentation of a 512 × 512 image takes less than a second on a modern GPU.

摘要 - 是一種CNN/fully convolutional network/很快。

學生角度

https://github.com/zhixuhao/unet

摘要 - 一大堆程式碼，可以讓我畢業的東西。

當被問為什麼要用U-net的時候

不知道

翻譯 - 我覺得這個技術可以讓我畢業。

結論

所以還是多讀論文，讀論文也不會很難，像今天就將摘要讀完了(並且獲得了一大堆問題)，明天開始讀前言吧~~

參考文獻

Unet原文
維基百科