U-Net is an architecture for semantic segmentation. It consists of a contracting path and an expansive path. The contracting path follows the typical architecture of a convolutional network. It consists of the repeated application of two 3x3 convolutions (unpadded convolutions), each followed by a rectified linear unit (ReLU) and a 2x2 max pooling operation with stride 2 for downsampling. At each downsampling step we double the number of feature channels. Every step in the expansive path consists of an upsampling of the feature map followed by a 2x2 convolution (“up-convolution”) that halves the number of feature channels, a concatenation with the correspondingly cropped feature map from the contracting path, and two 3x3 convolutions, each followed by a ReLU. The cropping is necessary due to the loss of border pixels in every convolution. At the final layer a 1x1 convolution is used to map each 64-component feature vector to the desired number of classes. In total the network has 23 convolutional layers.
相关学科: Semantic SegmentationMedical Image SegmentationFCNConvolutionSegNetBrain Tumor SegmentationTumor SegmentationLesion SegmentationResNetData Augmentation









Yoshua Bengio

429868 被引用,1063 篇论文

Andrew Zisserman

195560 被引用,885 篇论文

Xiang Zhang

138753 被引用,2111 篇论文

Xiangyu Zhang

115315 被引用,135 篇论文

Léon Bottou

98650 被引用,174 篇论文

Jian Yang

96983 被引用,1935 篇论文

Bruce R. Rosen

93870 被引用,768 篇论文

Luc Van Gool

91399 被引用,1409 篇论文

Paul M. Matthews

90175 被引用,752 篇论文

Daniel S. Berman

86611 被引用,1751 篇论文