AI engineering glossary · Computer vision
What is U-Net?
U-Net: A segmentation network shaped like a U: an encoder shrinks the image to capture context, a decoder expands it back, and skip connections copy detailed features from encoder to decoder. It works well even with small datasets, notably in medical imaging.
U-Net: an example
U-Net is widely used to outline organs and lesions in CT and MRI slices.
Related terms
- Semantic segmentation
- Transposed convolution
- Residual connection
More Computer vision terms
- Upsampling
- VGG
- Vision transformer
- YOLO
- Zero-shot learning
- 1x1 convolution
- Affine transformation of images
- AlexNet
Where you learn it
U-Net is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.