U-Net: Difference between revisions
m ty |
Stub sorting |
||
Line 12: | Line 12: | ||
[[Category:Deep learning]] |
[[Category:Deep learning]] |
||
[[Category:Neural networks]] |
[[Category:Neural networks]] |
||
{{Neuroscience-stub}} |
Revision as of 03:08, 20 May 2018
The U-Net is a Caffe-based 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.
Network architecture
The network consists of a contracting path and an expansive path, which gives it the u-shaped architecture. The contracting path is a typical convolutional network that consists of repeated application of convolutions, each followed by a rectified linear unit (ReLU) and a max pooling operation. During the contraction, the spatial information is reduced while feature information is increased. The expansive pathway combines the feature and spatial information through a sequence of up-convolutions and concatenations with high-resolution features from the contracting path.[3]
The basic articles on the system [1] [2] have been cited 1638 and 1086 times respectively on Google Scholar as of May 19, 2018[4]
References
- ^ a b Ronneberger, Olaf; Fischer, Philipp; Brox, Thomas (2015). "U-Net: Convolutional Networks for Biomedical Image Segmentation". arXiv:1505.04597 [cs.CV].
- ^ a b Long, J.; Shelhamer, E.; Darrell, T. (2014). "Fully convolutional networks for semantic segmentation". arXiv:1411.4038 [cs.CV].
- ^ "U-Net code".
- ^ [1] Google Scholar citation data