Galaxy Zoo Evo: 1 million human-annotated images of galaxies

TL;DR

Galaxy Zoo Evo provides a vast, detailed dataset of 823,000 galaxy images with 104 million labels, enabling advanced foundation models for astronomical image analysis and domain adaptation.

Contribution

This paper introduces Galaxy Zoo Evo, a large-scale, richly labeled galaxy image dataset designed for training and evaluating foundation models in astronomy.

Findings

Provides 104 million labels for 823,000 images

Includes specialized labels for tasks like lens detection

Serves as a benchmark for domain adaptation in astronomy

Abstract

We introduce Galaxy Zoo Evo, a labeled dataset for building and evaluating foundation models on images of galaxies. GZ Evo includes 104M crowdsourced labels for 823k images from four telescopes. Each image is labeled with a series of fine-grained questions and answers (e.g. "featured galaxy, two spiral arms, tightly wound, merging with another galaxy"). These detailed labels are useful for pretraining or finetuning. We also include four smaller sets of labels (167k galaxies in total) for downstream tasks of specific interest to astronomers, including finding strong lenses and describing galaxies from the new space telescope Euclid. We hope GZ Evo will serve as a real-world benchmark for computer vision topics such as domain adaption (from terrestrial to astronomical, or between telescopes) or learning under uncertainty from crowdsourced labels. We also hope it will support a new generation of foundation models for astronomy; such models will be critical to future astronomers seeking to better understand our universe.