Glossary · Deep learning
What is U-Net? Definition and meaning
A convolutional encoder-decoder with skip connections that preserves fine detail for pixel-level predictions.
Definition
U-Net: A convolutional encoder-decoder with skip connections that preserves fine detail for pixel-level predictions.
In short: Down, then up, with shortcuts.
When it is used
Image segmentation and the denoising network in many diffusion models.
Where it fits
U-Net belongs to Building blocks in the Deep learning topic. These are the other terms in the same group:
- Attention mechanism: A mechanism that computes weighted combinations of inputs, with weights based on relevance between queries and keys.
- Backpropagation: An algorithm that uses the chain rule to compute gradients of the loss with respect to every weight.
- Normalization layers: Layers that rescale activations to a standard range, stabilising and accelerating training.
- Dropout: A regularisation technique that zeroes random activations during training to prevent co-adaptation.
- Optimizers: Algorithms that update model parameters from gradients, such as SGD, momentum, Adam and AdamW.
- Word embeddings: Learned vector representations of words where similar words have similar vectors, as in Word2Vec and GloVe.
- Knowledge distillation: Training a compact model to match the outputs of a larger model, transferring much of its capability.
- Pruning: Removing weights, channels or layers that contribute little, to shrink and speed up a network.
Learn more
The full guide to U-Net explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.
Previous term: TurboQuant · Next term: UiPath