Zum Inhalt springen

Benutzer:Bschaich/U-Net

aus Wikipedia, der freien Enzyklopädie
Dies ist eine alte Version dieser Seite, zuletzt bearbeitet am 24. April 2018 um 11:12 Uhr durch 138.246.2.58 (Diskussion). Sie kann sich erheblich von der aktuellen Version unterscheiden.

The U-Net is a Caffee-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]

References

Vorlage:Reflist

  1. Vorlage:Cite arxiv
  2. Vorlage:Cite arxiv
  3. U-Net code.