# Practical Galaxy Morphology Tools from Deep Supervised Representation Learning

arXiv: https://arxiv.org/abs/2110.12735 · HTML: https://mlsanity.com/paper/2110.12735/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 38 references that are in the map.
- First posted on arXiv 25 Oct 2021.

## Builds on (most cited first, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Deep Ensembles: A Loss Landscape Perspective](https://mlsanity.com/paper/1912.02757/) (2019)
- [A Neural Scaling Law from the Dimension of the Data Manifold](https://mlsanity.com/paper/2004.10802/) (2020)
- [modAL: A modular active learning framework for Python](https://mlsanity.com/paper/1805.00979/) (2018)
- [Practical Text Classification With Large Pre-Trained Language Models](https://mlsanity.com/paper/1812.01207/) (2018)
- [Survey2Survey: A deep learning generative model approach for cross-survey image mapping](https://mlsanity.com/paper/2011.07124/) (2020)
- [Improve black-box sequential anomaly detector relevancy with limited user feedback](https://mlsanity.com/paper/2009.07241/) (2020)

## Built on by (most cited first, 15 of 15)

- [Towards Galaxy Foundation Models with Hybrid Contrastive Learning](https://mlsanity.com/paper/2206.11927/) (2022)
- [AstroPT: Scaling Large Observation Models for Astronomy](https://mlsanity.com/paper/2405.14930/) (2024)
- [A brief review of contrastive learning applied to astrophysics](https://mlsanity.com/paper/2306.05528/) (2023)
- [CosmoCLIP: Generalizing Large Vision-Language Models for Astronomical Imaging](https://mlsanity.com/paper/2407.07315/) (2024)
- [GalaxAlign: Mimicking Citizen Scientists' Multimodal Guidance for Galaxy Morphology Analysis](https://mlsanity.com/paper/2411.19475/) (2024)
- [A two-steps approach to improve the performance of Android malware detectors](https://mlsanity.com/paper/2205.08265/) (2022)
- [A review of unsupervised learning in astronomy](https://mlsanity.com/paper/2406.17316/) (2024)
- [Rare Galaxy Classes Identified In Foundation Model Representations](https://mlsanity.com/paper/2312.02910/) (2023)
- [A Classifier-Based Approach to Multi-Class Anomaly Detection Applied to Astronomical Time-Series](https://mlsanity.com/paper/2408.08888/) (2024)
- [From fat droplets to floating forests: cross-domain transfer learning using a PatchGAN-based segmentation model](https://mlsanity.com/paper/2211.03937/) (2022)
- [Deep supervised hashing for fast retrieval of radio image cubes](https://mlsanity.com/paper/2309.00932/) (2023)
- [TCuPGAN: A novel framework developed for optimizing human-machine interactions in citizen science](https://mlsanity.com/paper/2311.14177/) (2023)
- [Simulation-Based Pretraining and Domain Adaptation for Astronomical Time Series with Minimal Labeled Data](https://mlsanity.com/paper/2510.12958/) (2025)
- [Pre-training vision models for the classification of alerts from wide-field time-domain surveys](https://mlsanity.com/paper/2512.11957/) (2025)
- [Shared Geometry Is Not Shared Physics: A Layerwise Test of the Platonic Representation Hypothesis in Astronomy](https://mlsanity.com/paper/2610.04130/) (2026)

## Abstract (arXiv)

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.