Live briefing
Everything about U-Net
Type of convolutional neural network
U-Net is a convolutional neural network that was developed for image segmentation. The network is based on a fully convolutional neural network whose architecture was modified and extended to work with fewer training images and to yield more precise segmentation. Segmentation of a 512 × 512 image takes less than a second on a modern (2015) GPU using the U-Net architecture. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: U-NetA 5-minute orientation
- Skim a recent paper: TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformersInfluential work since 2022
- Pick up a classic book: Mariner 9 control net of Mars: April, 1973The most-reprinted book on the subject
- Read the landmark paper: Regularization and Variable Selection Via the Elastic NetCited 17,874 times
- Go sideways: Thomas BroxA closely related topic
- Go sideways: Binding siteA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
Regularization and Variable Selection Via the Elastic Net
nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation
On the separation of net ecosystem exchange into assimilation and ecosystem respiration: review and improved algorithm
Climate-Driven Increases in Global Terrestrial Net Primary Production from 1982 to 1999
Are Government Bonds Net Wealth?
Road Extraction by Deep Residual U-Net
The Contract Net Protocol: High-Level Communication and Control in a Distributed Problem Solver
Drought-Induced Reduction in Global Terrestrial Net Primary Production from 2000 Through 2009
🆕 Influential since 2022
TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers
UIU-Net: U-Net in U-Net for Infrared Small Object Detection
Medical Image Segmentation Review: The Success of U-Net
DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention
UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-Wise Perspective with Transformer
📚 Books worth reading
- 📕Mariner 9 control net of Mars: April, 1973Merton E. Davies · 1973
- 📕Mariner 9 control net of Mars: June 1973Merton E. Davies · 1973
- 📕A preliminary control net of MarsMerton E. Davies · 1970
- 📕Control point measurements on Mariner 10 pictures of MercuryMerton E Davies · 1976
- 📕Identification of control points on MercuryMerton E Davies · 1976
- 📕Control net of MarsMerton E. Davies · 1978
- 📕Control point measurements on Mariner 9 picturesMerton E. Davies · 1973
#NewsfailJamie Kilstein, Allison Kilkenny · 2014
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Thomas Brox Thomas Brox (born 1976) is a computer scientist and professor of pattern recognition and image processing at the University of Freiburg, where he heads…
- Binding site In biochemistry and molecular biology, a binding site is a region on a macromolecule such as a protein that binds to another molecule with specificity…
- Convolutional neural network A convolutional neural network (CNN) is a type of feedforward neural network that learns features via filter (or kernel) optimization. This type of deep…
- Neural architecture search Neural architecture search (NAS) is a technique for automating the design of artificial neural networks (ANN), a widely used model in the field of machine…
- Deep learning in photoacoustic imaging Photoacoustic imaging (PA) is based on the photoacoustic effect, in which optical absorption causes a rise in temperature, which causes a subsequent rise…
- Graph neural network Graph neural networks (GNNs) are artificial neural networks designed for tasks whose inputs are graphs. Because graphs usually do not have a canonical…
- Object detection Object detection is a computer technology related to computer vision and image processing that deals with detecting instances of semantic objects of a…
- Vision transformer A vision transformer (ViT) is a transformer designed for computer vision. A ViT decomposes an input image into a series of patches (rather than text into…