计算机科学
人工智能
分割
边距(机器学习)
滑动窗口协议
背景(考古学)
路径(计算)
网(多面体)
图像(数学)
网络体系结构
模式识别(心理学)
窗口(计算)
图像分割
卷积神经网络
深度学习
推论
计算机视觉
机器学习
计算机网络
数学
万维网
生物
古生物学
几何学
作者
Olaf Ronneberger,Philipp Fischer,Thomas Brox
出处
期刊:Cornell University - arXiv
日期:2015-05-18
被引量:230
标识
DOI:10.48550/arxiv.1505.04597
摘要
There is large consent that successful training of deep networks requires many thousand annotated training samples. 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. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. 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. 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. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net .
科研通智能强力驱动
Strongly Powered by AbleSci AI