Evaluating Bayesian deep learning for radio galaxy classification
Not on the map. Why?
Abstract (arXiv)
The radio astronomy community is rapidly adopting deep learning techniques to deal with the huge data volumes expected from the next generation of radio observatories. Bayesian neural networks (BNNs) provide a principled way to model uncertainty in the predictions made by such deep learning models and will play an important role in extracting well-calibrated uncertainty estimates on their outputs. In this work, we evaluate the performance of different BNNs against the following criteria: predictive performance, uncertainty calibration and distribution-shift detection for the radio galaxy classification problem.
Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 26 of its 57 references that are in the map. First posted on arXiv 28 May 2024.
Builds on
26 of 57 references.
References · 26
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,902
- 2016Variational Inference: A Review for Statisticianscited by 1,469
- 2020Energy-based Out-of-distribution Detectioncited by 1,297
- 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 910
- 2015Weight Uncertainty in Neural Networkscited by 554
- 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 361
- 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
- 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
- 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 125
- 2020Improving model calibration with accuracy versus uncertainty optimizationcited by 123
- 2021Scalable Marginal Likelihood Estimation for Model Selection in Deep Learningcited by 105
- 2021The Bayesian Learning Rulecited by 98
14 more
- 2024Variational Learning is Effective for Large Deep Networkscited by 62
- 2020Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splittingcited by 54
- 2021Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxiescited by 40
- 2019Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inferencecited by 35
- 2021Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effectcited by 22
- 2023On the Convergence of Black-Box Variational Inferencecited by 22
- 2020Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shiftcited by 21
- 2023Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shiftcited by 20
- 2018Good Initializations of Variational Bayes for Deep Modelscited by 11
- 2020Attention-gating for improved radio galaxy classificationcited by 9
- 2022Radio Galaxy Zoo: Using semi-supervised learning to leverage large unlabelled data-sets for radio galaxy classification under data-set shiftcited by 8
- 2017Proximity Variational Inferencecited by 6
- 2023MiraBest: A Dataset of Morphologically Classified Radio Galaxies for Machine Learningcited by 4
- 2022Quantifying Uncertainty in Deep Learning Approaches to Radio Galaxy Classificationcited by 3
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.