Estimating Galactic Distances From Images Using Self-supervised Representation Learning

TL;DR

This paper introduces a self-supervised learning approach to estimate galaxy distances from images, achieving comparable or better accuracy than supervised methods while using less labeled data.

Contribution

It presents a contrastive self-supervised framework with domain-specific augmentations for galaxy images, outperforming state-of-the-art supervised methods in redshift estimation.

Findings

Pretraining on unlabeled data with fine-tuning matches supervised accuracy.

Fine-tuning on SDSS data surpasses current supervised methods.

Representations enable fast similarity searches for galaxy images.

Abstract

We use a contrastive self-supervised learning framework to estimate distances to galaxies from their photometric images. We incorporate data augmentations from computer vision as well as an application-specific augmentation accounting for galactic dust. We find that the resulting visual representations of galaxy images are semantically useful and allow for fast similarity searches, and can be successfully fine-tuned for the task of redshift estimation. We show that (1) pretraining on a large corpus of unlabeled data followed by fine-tuning on some labels can attain the accuracy of a fully-supervised model which requires 2-4x more labeled data, and (2) that by fine-tuning our self-supervised representations using all available data labels in the Main Galaxy Sample of the Sloan Digital Sky Survey (SDSS), we outperform the state-of-the-art supervised learning method.