Practical galaxy morphology tools from deep supervised representation learning

Simple item page
dc.contributor.authorWalmsley, Mike
dc.contributor.authorScaife, Anna M. M.
dc.contributor.authorLochner, Michelle
dc.date.accessioned2022-07-21T09:52:07Z
dc.date.available2022-07-21T09:52:07Z
dc.date.issued2022
dc.description.abstractAstronomers 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).en_US
dc.identifier.citationWalmsley, M. et al. (2022). Practical galaxy morphology tools from deep supervised representation learning. Monthly Notices of the Royal Astronomical Society, 513(2), 1581-1599. 10.1093/mnras/stac525en_US
dc.identifier.issn1365-2966
dc.identifier.uri10.1093/mnras/stac525
dc.identifier.urihttp://hdl.handle.net/10566/7622
dc.language.isoenen_US
dc.publisherOxford University Pressen_US
dc.subjectSoftwareen_US
dc.subjectAstrophysicsen_US
dc.subjectData handlingen_US
dc.subjectMorphologyen_US
dc.subjectGalaxiesen_US
dc.titlePractical galaxy morphology tools from deep supervised representation learningen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
walmsley_practical galaxy morphology tools_2022.pdf
Size:
4.01 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Research Articles (Physics)