Quantifying Uncertainty in Deep Learning Approaches to Radio Galaxy Classification

Abstract

In this work we use variational inference to quantify the degree of uncertainty in deep learning model predictions of radio galaxy classification. We show that the level of model posterior variance for individual test samples is correlated with human uncertainty when labelling radio galaxies. We explore the model performance and uncertainty calibration for different weight priors and suggest that a sparse prior produces more well-calibrated uncertainty estimates. Using the posterior distributions for individual weights, we demonstrate that we can prune 30% of the fully-connected layer weights without significant loss of performance by removing the weights with the lowest signal-to-noise ratio. A larger degree of pruning can be achieved using a Fisher information based ranking, but both pruning methods affect the uncertainty calibration for Fanaroff-Riley type I and type II radio galaxies differently. Like other work in this field, we experience a cold posterior effect, whereby the posterior must be down-weighted to achieve good predictive performance. We examine whether adapting the cost function to accommodate model misspecification can compensate for this effect, but find that it does not make a significant difference. We also examine the effect of principled data augmentation and find that this improves upon the baseline but also does not compensate for the observed effect. We interpret this as the cold posterior effect being due to the overly effective curation of our training sample leading to likelihood misspecification, and raise this as a potential issue for Bayesian deep learning approaches to radio galaxy classification in future.

accepted by MNRAS

References in corpus (9)

• Science with ASKAP - the Australian Square Kilometre Array Pathfinder
• Revisiting the Fanaroff-Riley dichotomy and radio-galaxy morphology with the LOFAR Two-Metre Sky Survey (LoTSS)
• Classifying Radio Galaxies with Convolutional Neural Network
• Luminosity function, sizes and FR dichotomy of radio-loud AGN
• Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks
• Attention-gating for improved radio galaxy classification
• Science with the Murchison Widefield Array: Phase I Results and Phase II Opportunities
• Rapid sorting of radio galaxy morphology using Haralick features
• Structured Variational Inference for Simulating Populations of Radio Galaxies

Cited by in corpus (1)

• Radio Galaxy Zoo: Using semi-supervised learning to leverage large unlabelled data-sets for radio galaxy classification under data-set shift