UNet Transformer

Introduced by Hatamizadeh et al. in UNETR: Transformers for 3D Medical Image Segmentation

UNETR, or UNet Transformer, is a Transformer-based architecture for medical image segmentation that utilizes a pure transformer as the encoder to learn sequence representations of the input volume -- effectively capturing the global multi-scale information. The transformer encoder is directly connected to a decoder via skip connections at different resolutions like a U-Net to compute the final semantic segmentation output.

Source: UNETR: Transformers for 3D Medical Image Segmentation

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Semantic Segmentation	9	19.57%
Image Segmentation	8	17.39%
Medical Image Segmentation	6	13.04%
Tumor Segmentation	3	6.52%
Self-Supervised Learning	2	4.35%
Instance Segmentation	1	2.17%
Zero-shot Generalization	1	2.17%
Zero Shot Segmentation	1	2.17%
Specificity	1	2.17%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
1x1 Convolution	Convolutions
Batch Normalization	Normalization
Convolution	Convolutions
Multi-Head Attention	Attention Modules
Position-Wise Feed-Forward Layer	Feedforward Networks
ReLU	Activation Functions
Residual Connection	Skip Connections
Scaled Dot-Product Attention	Attention Mechanisms
U-Net	Semantic Segmentation Models

Categories

Add Remove

Medical Image Models