AI Blog

AI Blog

by Michele Laurelli

Back to Glossary

U-Net

/juː nɛt/
Architecture
Definition

A CNN architecture designed for biomedical image segmentation, featuring an encoder-decoder structure with skip connections.

U-Net has a U-shaped architecture with contracting path (encoder) and expansive path (decoder). Skip connections preserve spatial information, making it excellent for segmentation tasks.

Examples

1

Medical image segmentation

2

Cell detection

3

Satellite image analysis

Related Terms

Semantic Segmentation

A computer vision task that assigns a class label to every pixel in an image.

Encoder-Decoder

An architecture where an encoder processes input into a representation and a decoder generates output from it.

Michele Laurelli - AI Research & Engineering