A brief review of contrastive learning applied to astrophysics

Huertas-Company, Marc; Sarmiento, Regina; Knapen, Johan H.
Bibliographical reference

RAS Techniques and Instruments

Advertised on:
Number of authors
IAC number of authors
Refereed citations
Reliable tools to extract patterns from high-dimensionality spaces are becoming more necessary as astronomical data sets increase both in volume and complexity. Contrastive Learning is a self-supervised machine learning algorithm that extracts informative measurements from multidimensional data sets, which has become increasingly popular in the computer vision and Machine Learning communities in recent years. To do so, it maximizes the agreement between the information extracted from augmented versions of the same input data, making the final representation invariant to the applied transformations. Contrastive Learning is particularly useful in astronomy for removing known instrumental effects and for performing supervised classifications and regressions with a limited amount of available labels, showing a promising avenue towards Foundation Models. This short review paper briefly summarizes the main concepts behind contrastive learning and reviews the first promising applications to astronomy. We include some practical recommendations on which applications are particularly attractive for contrastive learning.
Related projects
Project Image
Spiral Galaxies: Evolution and Consequences
Our small group is well known and respected internationally for our innovative and important work on various aspects of the structure and evolution of nearby spiral galaxies. We primarily use observations at various wavelengths, exploiting synergies that allow us to answer the most pertinent questions relating to what the main properties of
Johan Hendrik
Knapen Koelstra
Group members
Traces of Galaxy Formation: Stellar populations, Dynamics and Morphology
We are a large, diverse, and very active research group aiming to provide a comprehensive picture for the formation of galaxies in the Universe. Rooted in detailed stellar population analysis, we are constantly exploring and developing new tools and ideas to understand how galaxies came to be what we now observe.
Martín Navarro