論文原文：U-Net: Convolutional Networks for Biomedical Image Segmentation (arxiv.org)

英文是純手打的！論文原文的summarizing and paraphrasing?？赡軙霈F(xiàn)難以避免的拼寫錯誤和語法錯誤，若有發(fā)現(xiàn)歡迎評論指正！文章偏向于筆記，謹(jǐn)慎食用！

1. 原文逐段精讀

1.1. Abstract

? ? ? ? ①Reasonable use of annotation samples

? ? ? ? ②"The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization"

? ? ? ? ③This model is for segmenting?neuronal structures in electron microscopic stacks

? ? ? ? ④This model peforms great in small training sample?

1.2. Introduction

? ? ? ? ①The expectations for machine learning and deep learning in medicine often lie not in classification accuracy, but in region segmentation and other aspects

? ? ? ? ②They consider the sliding-window model by Ciresan et al. as slow in training and inaccuracy brought by maxpooling

? ? ? ? ③?U-Net takes upsampling instead of pooling

? ? ? ? ④什么重疊貼圖策略？？我沒能明白，為啥這樣就能預(yù)測

? ? ? ? ⑤They use?elastic deformations to augment there data, which keeps the?invariance

1.3.?Network Architecture

? ? ? ? ①The whole framework:?

? ? ? ? ②3*3 convolutions include no padding

? ? ? ? ③Stride of maxpooling is 2

? ? ? ? ④Double the number of channels?when downsampling

? ? ? ? ⑤Up-conv 2*2 halves the number of feature channels

1.4.?Training

1.4.1.?Data Augmentation

1.5.?Experiments

1.6.?Conclusion

2. 代碼

3. Reference List

Ronneberger, O., Fischer, P. & Brox, T. (2015) 'U-Net: Convolutional Networks for Biomedical Image Segmentation',?MICCAI 2015:?Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pp 234–241. doi:?U-Net: Convolutional Networks for Biomedical Image Segmentation | SpringerLink?