ML method · Self-supervised

Self-Supervised Learning

Training a model on unlabelled data by inventing a task it can grade itself on — predicting a hidden part of an image, or telling two views of the same object apart. It is powerful in astronomy, where raw data is abundant but expert labels are scarce.

Highlights

›Learning from abundant data without labels

Representation Learning
Foundation Models

Used across astro-ML

Representation Learning
Foundation Models

Knowledge connections

Associated withRepresentation Learning
Associated withRepresentation Learning
Associated withFoundation Models
Associated withFoundation Models

Sources

Facts on this topic will be cited from these primary and reference sources.

NASANational Aeronautics and Space Administration
Mission data, planetary science, space telescopes, and public-domain imagery.
Most NASA-produced imagery is in the public domain; individual items are checked for usage terms before publication.

Loading…

Self-Supervised Learning

Highlights

Methods, data & targets

Used across astro-ML

Knowledge connections

Sources

Self-Supervised Learning

Highlights

Methods, data & targets

Used across astro-ML

Knowledge connections

Sources