Galaxy Morphological Classification with Efficient Vision Transformer

TL;DR

This paper investigates the application of Vision Transformer models to classify galaxy morphologies, demonstrating competitive performance especially on smaller and fainter galaxies, and providing a new tool for future astronomical surveys.

Contribution

First application of Vision Transformer to galaxy morphology classification, showing promising results and potential for future large-scale surveys.

Findings

ViT achieves competitive accuracy with CNNs.

ViT excels at classifying small and faint galaxies.

Open-source implementation available for community use.

Abstract

Quantifying the morphology of galaxies has been an important task in astrophysics to understand the formation and evolution of galaxies. In recent years, the data size has been dramatically increasing due to several on-going and upcoming surveys. Labeling and identifying interesting objects for further investigations has been explored by citizen science through the Galaxy Zoo Project and by machine learning in particular with the convolutional neural networks (CNNs). In this work, we explore the usage of Vision Transformer (ViT) for galaxy morphology classification for the first time. We show that ViT could reach competitive results compared with CNNs, and is specifically good at classifying smaller-sized and fainter galaxies. With this promising preliminary result, we believe the ViT network architecture can be an important tool for galaxy morphological classification for the next generation surveys. Our open source, is publicly available at \url{https://github.com/sliao-mi-luku/Galaxy-Zoo-Classification}