Skip to content
AI360Xpert
Computer Vision
Visual explainer

U-Net Segmentation

A neural network architecture that outputs pixel-wise classification maps.

Image to Mask
Image to Mask

U-Net is an encoder-decoder architecture designed to output a segmentation mask, mapping every pixel of an input image to a specific class.

Contracting Path
Contracting Path

The left side of the network (encoder) gradually reduces the spatial dimensions of the image while increasing the number of feature channels, capturing the "what" (context).

Expanding Path
Expanding Path

The right side (decoder) progressively restores the spatial dimensions, reconstructing the "where" (localization) to output a full-resolution mask.

Skip Connections
Skip Connections

To recover fine-grained spatial details lost during downsampling, U-Net uses skip connections. These transfer high-resolution features directly from the encoder to the decoder, merging context with precise localization.