Galaxy Morphological Classification with Deep Learning
Nov 15, 2024·
·
1 min read
Matthieu Le Lain
Galaxy morphological classification (spiral, elliptical, or irregular?) is one of the most natural applications of computer vision in astronomy. Datasets like Galaxy Zoo and Galaxy10 DECaLS provide crowd-sourced morphological labels for thousands of galaxies and serve as standard benchmarks.
In my work with Sébastien Lefèvre, we compared several pre-trained foundation models (ViT, SwinV2, BEiT, DINOv2) on Galaxy10 DECaLS to see how well they transfer to astronomical images. The short answer: surprisingly well, but the fine-tuning strategy matters a lot. These results were presented at EAS 2024 and GRETSI 2025, with a detailed analysis in the companion paper.
Authors
AI for astronomy & astrophysics
PhD student at IRISA, Université Bretagne Sud (expected 2026), and lecturer in computer science,
working on foundation models for astronomy and astrophysics, with a broader interest
in deep learning applied to scientific data.
Also contributing to the UniverseTBD collaboration on vision-language models for astronomy.