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.
Source: U-Net: Convolutional Networks for Biomedical Image SegmentationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 114 | 11.86% |
Image Segmentation | 73 | 7.60% |
Denoising | 57 | 5.93% |
Image Generation | 53 | 5.52% |
Decoder | 46 | 4.79% |
Medical Image Segmentation | 42 | 4.37% |
Tumor Segmentation | 21 | 2.19% |
Deep Learning | 18 | 1.87% |
Computational Efficiency | 16 | 1.66% |
Component | Type |
|
---|---|---|
Concatenated Skip Connection
|
Skip Connections | |
Convolution
|
Convolutions | |
Max Pooling
|
Pooling Operations | |
ReLU
|
Activation Functions |