AI engineering glossary · Deep learning core
What is instance normalisation?
Instance normalisation: A normalisation that standardises each channel of each individual example separately, using its own spatial mean and variance. It became popular in image style-transfer and generation models where per-image contrast should be removed.
Instance normalisation: an example
Each feature map of one photo is normalised alone, unaffected by other images in the batch.
Related terms
More Deep learning core terms
- Iteration
- Label smoothing
- LAMB optimiser
- Layer
- Layer normalisation
- Leaky ReLU
- Learning rate finder
- LeCun initialisation
Where you learn it
Instance normalisation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.