Glossary
What is MoCo? Definition and meaning
Builds a large dictionary of negatives with a slowly updated momentum encoder and a queue.
Definition
MoCo: Builds a large dictionary of negatives with a slowly updated momentum encoder and a queue.
In short: Contrastive learning with a momentum encoder and queue.
When it is used
Self-supervised pre-training when large batches are not available.
Learn more
The full guide to MoCo 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: MLflow · Next term: Model cards