# Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning

arXiv: https://arxiv.org/abs/1905.07424 · HTML: https://mlsanity.com/paper/1905.07424/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2019.

## Built on by (most cited first, 22 of 22)

- [Mining for Strong Gravitational Lenses with Self-supervised Learning](https://mlsanity.com/paper/2110.00023/) (2021)
- [DeepAstroUDA: Semi-Supervised Universal Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection](https://mlsanity.com/paper/2302.02005/) (2023)
- [Low-Budget Simulation-Based Inference with Bayesian Neural Networks](https://mlsanity.com/paper/2408.15136/) (2024)
- [GalaxAlign: Mimicking Citizen Scientists' Multimodal Guidance for Galaxy Morphology Analysis](https://mlsanity.com/paper/2411.19475/) (2024)
- [Learning Uncertainty with Artificial Neural Networks for Improved Predictive Process Monitoring](https://mlsanity.com/paper/2206.06317/) (2022)
- [Deep learning with photosensor timing information as a background rejection method for the Cherenkov Telescope Array](https://mlsanity.com/paper/2103.06054/) (2021)
- [Revisiting Citizen Science Through the Lens of Hybrid Intelligence](https://mlsanity.com/paper/2104.14961/) (2021)
- [A Comparison of Deep Learning Architectures for Optical Galaxy Morphology Classification](https://mlsanity.com/paper/2111.04353/) (2021)
- [Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels](https://mlsanity.com/paper/2211.06903/) (2022)
- [Discovering Galaxy Features via Dataset Distillation](https://mlsanity.com/paper/2311.17967/) (2023)
- [A review of unsupervised learning in astronomy](https://mlsanity.com/paper/2406.17316/) (2024)
- [AstronomicAL: An interactive dashboard for visualisation, integration and classification of data using Active Learning](https://mlsanity.com/paper/2109.05207/) (2021)
- [Using Machine Learning to Determine Morphologies of z<1 AGN Host Galaxies in the Hyper Suprime-Cam Wide Survey](https://mlsanity.com/paper/2212.09984/) (2022)
- [Exploring the Universe with SNAD: Anomaly Detection in Astronomy](https://mlsanity.com/paper/2410.18875/) (2024)
- [Automatic Machine Learning Framework to Study Morphological Parameters of AGN Host Galaxies within z < 1.4 in the Hyper Supreme-Cam Wide Survey](https://mlsanity.com/paper/2501.15739/) (2025)
- [Category-based Galaxy Image Generation via Diffusion Models](https://mlsanity.com/paper/2506.16255/) (2025)
- [Applications of AI in Astronomy](https://mlsanity.com/paper/2212.01493/) (2022)
- [Deep Learning Segmentation of Spiral Arms and Bars](https://mlsanity.com/paper/2312.02908/) (2023)
- [Bayesian and Convolutional Networks for Hierarchical Morphological Classification of Galaxies](https://mlsanity.com/paper/2405.02366/) (2024)
- [Multi-scale gridded Gabor attention for cirrus segmentation](https://mlsanity.com/paper/2407.08852/) (2024)
- [Active Learning for Planet Habitability Classification under Extreme Class Imbalance](https://mlsanity.com/paper/2602.23666/) (2026)
- [Epistemic Uncertainty Is Not the Reducible Kind](https://mlsanity.com/paper/2606.12646/) (2026)

## Abstract (arXiv)

We use Bayesian convolutional neural networks and a novel generative model of Galaxy Zoo volunteer responses to infer posteriors for the visual morphology of galaxies. Bayesian CNN can learn from galaxy images with uncertain labels and then, for previously unlabelled galaxies, predict the probability of each possible label. Our posteriors are well-calibrated (e.g. for predicting bars, we achieve coverage errors of 11.8% within a vote fraction deviation of 0.2) and hence are reliable for practical use. Further, using our posteriors, we apply the active learning strategy BALD to request volunteer responses for the subset of galaxies which, if labelled, would be most informative for training our network. We show that training our Bayesian CNNs using active learning requires up to 35-60% fewer labelled galaxies, depending on the morphological feature being classified. By combining human and machine intelligence, Galaxy Zoo will be able to classify surveys of any conceivable scale on a timescale of weeks, providing massive and detailed morphology catalogues to support research into galaxy evolution.