Rare Galaxy Classes Identified In Foundation Model Representations
Astrophysics of Galaxies
2023-12-06 v1 Computer Vision and Pattern Recognition
Abstract
We identify rare and visually distinctive galaxy populations by searching for structure within the learned representations of pretrained models. We show that these representations arrange galaxies by appearance in patterns beyond those needed to predict the pretraining labels. We design a clustering approach to isolate specific local patterns, revealing groups of galaxies with rare and scientifically-interesting morphologies.
Cite
@article{arxiv.2312.02910,
title = {Rare Galaxy Classes Identified In Foundation Model Representations},
author = {Mike Walmsley and Anna M. M. Scaife},
journal= {arXiv preprint arXiv:2312.02910},
year = {2023}
}
Comments
Accepted at Machine Learning and the Physical Sciences Workshop, NeurIPS 2023