Practical Galaxy Morphology Tools from Deep Supervised Representation Learning

Abstract

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% 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 datasets 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.

20 pages plus appendix. Accepted to MNRAS (open-access DOI below). Code, documentation, pretrained models: https://github.com/mwalmsley/zoobot (PyTorch and TensorFlow)

References in corpus (16)

• scikit-image: Image processing in Python
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• A Classical Morphological Analysis of Galaxies in the Spitzer Survey of Stellar Structure in Galaxies (S4G)
• Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy
• Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• Galaxy Zoo: comparing the demographics of spiral arm number and a new method for correcting redshift bias
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• Galaxy Morphology Network: A Convolutional Neural Network Used to Study Morphology and Quenching in $\sim 100,000$ SDSS and $\sim 20,000$ CANDELS Galaxies
• Galactic Rings Revisited. I. CVRHS Classifications of 3962 Ringed Galaxies from the Galaxy Zoo 2 Database
• Anomaly detection in Hyper Suprime-Cam galaxy images with generative adversarial networks
• A Comprehensive Examination of the Optical Morphologies of 719 Isolated Galaxies in the AMIGA Sample
• Capturing the physics of MaNGA galaxies with self-supervised Machine Learning
• Automatic detection of full ring galaxy candidates in SDSS
• Morphology-assisted galaxy mass-to-light predictions using deep learning
• Survey2Survey: A deep learning generative model approach for cross-survey image mapping

Cited by in corpus (4)

• A unique, ring-like radio source with quadrilateral structure detected with machine learning
• Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features
• Analysis of Ring Galaxies Detected Using Deep Learning with Real and Simulated Data
• Learning to Detect Interesting Anomalies