Practical galaxy morphology tools from deep supervised representation learning

Mike Walmsley, Anna M.M. Scaife, Chris Lintott, Michelle Lochner, Verlon Etsebeth, Tobias Géron, Hugh Dickinson, Lucy Fortson, Sandor Kruk, Karen L. Masters, Kameswara Bharadwaj Mantha, Brooke D. Simmons

Research output: Contribution to journalArticlepeer-review

15 Scopus citations


Astronomers have typically set out to solve supervised machine learning problems by creating their own representations from scratch. We show that deep learning models trained to answer every Galaxy Zoo DECaLS question learn meaningful semantic representations of galaxies that are useful for new tasks on which the models were never trained. We exploit these representations to outperform several recent approaches at practical tasks crucial for investigating large galaxy samples. The first task is identifying galaxies of similar morphology to a query galaxy. Given a single galaxy assigned a free text tag by humans (e.g. '#diffuse'), we can find galaxies matching that tag for most tags. The second task is identifying the most interesting anomalies to a particular researcher. Our approach is 100 per cent accurate at identifying the most interesting 100 anomalies (as judged by Galaxy Zoo 2 volunteers). The third task is adapting a model to solve a new task using only a small number of newly labelled galaxies. Models fine-tuned from our representation are better able to identify ring galaxies than models fine-tuned from terrestrial images (ImageNet) or trained from scratch. We solve each task with very few new labels; either one (for the similarity search) or several hundred (for anomaly detection or fine-tuning). This challenges the longstanding view that deep supervised methods require new large labelled data sets for practical use in astronomy. To help the community benefit from our pretrained models, we release our fine-tuning code zoobot. Zoobot is accessible to researchers with no prior experience in deep learning.

Original languageEnglish (US)
Pages (from-to)1581-1599
Number of pages19
JournalMonthly Notices of the Royal Astronomical Society
Issue number2
StatePublished - Jun 1 2022

Bibliographical note

Publisher Copyright:
© 2022 The Author(s).


  • galaxies: evolution
  • galaxies: general
  • methods: data analysis
  • software: data analysis
  • software: public release


Dive into the research topics of 'Practical galaxy morphology tools from deep supervised representation learning'. Together they form a unique fingerprint.

Cite this