Deep Learning

U-Net

An encoder–decoder architecture designed for precise image segmentation.

U-Net first compresses an image into high-level features and then expands those features back to the original resolution. Skip connections transfer fine spatial details from the encoder to matching decoder stages.

The design produces accurate pixel-level predictions and was originally developed for medical-image segmentation. U-Net variants are also widely used inside diffusion-based image-generation systems.

Also in Deep Learning

CNN RNN LSTM Transformers Auto Encoders Deep RL

JOIN NOW

Begin the first module

It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.

See the curriculum

Join any time · Build AI skills at your pace