Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks

Abstract

Weight sharing in convolutional neural networks (CNNs) ensures that their feature maps will be translation-equivariant. However, although conventional convolutions are equivariant to translation, they are not equivariant to other isometries of the input image data, such as rotation and reflection. For the classification of astronomical objects such as radio galaxies, which are expected statistically to be globally orientation invariant, this lack of dihedral equivariance means that a conventional CNN must learn explicitly to classify all rotated versions of a particular type of object individually. In this work we present the first application of group-equivariant convolutional neural networks to radio galaxy classification and explore their potential for reducing intra-class variability by preserving equivariance for the Euclidean group E(2), containing translations, rotations and reflections. For the radio galaxy classification problem considered here, we find that classification performance is modestly improved by the use of both cyclic and dihedral models without additional hyper-parameter tuning, and that a D16 equivariant model provides the best test performance. We use the Monte Carlo Dropout method as a Bayesian approximation to recover epistemic uncertainty as a function of image orientation and show that E(2)-equivariant models are able to reduce variations in model confidence as a function of rotation.

11 pages, 6 figures, accepted MNRAS

References in corpus (13)

• astroquery: An Astronomical Web-Querying Package in Python
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Science with ASKAP - the Australian Square Kilometre Array Pathfinder
• Classifying Radio Galaxies with Convolutional Neural Network
• Dynamic Routing Between Capsules
• Galaxy Zoo: Chiral correlation function of galaxy spins
• Probing the Large-Scale Structure Around the Most Distant Galaxy Clusters from the Massive Cluster Survey
• Attention-gating for improved radio galaxy classification
• Science with the Murchison Widefield Array: Phase I Results and Phase II Opportunities
• Radio Galaxy Zoo: Cosmological Alignment of Radio Sources
• Galaxy spin direction distribution in HST and SDSS show similar large-scale asymmetry
• Alignment of Radio Galaxy Axes using FIRST Catalogue
• Alignment in the orientation of LOFAR radio sources

Cited by in corpus (27)

• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Translation and Rotation Equivariant Normalizing Flow (TRENF) for Optimal Cosmological Analysis
• Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations
• A method to challenge symmetries in data with self-supervised learning
• A Quick Look at the 3GHz Radio Sky. II. Hunting for DRAGNs in the VLA Sky Survey
• Generalization capabilities of translationally equivariant neural networks
• A Multimodal Dataset and Benchmark for Radio Galaxy and Infrared Host Detection
• Quantifying Uncertainty in Deep Learning Approaches to Radio Galaxy Classification
• Feature Guided Training and Rotational Standardisation for the Morphological Classification of Radio Galaxies
• Morphological Classification of Radio Galaxies with wGAN-supported Augmentation
• HOLISMOKES -- XI. Evaluation of supervised neural networks for strong-lens searches in ground-based imaging surveys
• Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds
• Finding AGN remnant candidates based on radio morphology with machine learning
• Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures
• Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1
• Rotation and flipping invariant self-organizing maps with astronomical images: A cookbook and application to the VLA Sky Survey QuickLook images
• Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features
• Morphological Classification of Radio Galaxies using Semi-Supervised Group Equivariant CNNs
• Radio Galaxy Zoo: Using semi-supervised learning to leverage large unlabelled data-sets for radio galaxy classification under data-set shift
• E(2)-Equivariant Features in Machine Learning for Morphological Classification of Radio Galaxies
• Radio Halo Detection in MWA Data using Deep Neural Networks and Generative Data Augmentation
• Weight Pruning and Uncertainty in Radio Galaxy Classification
• E(2) Equivariant Self-Attention for Radio Astronomy
• Can semi-supervised learning reduce the amount of manual labelling required for effective radio galaxy morphology classification?
• Radio Galaxy Zoo: Giant Radio Galaxy Classification using Multi-Domain Deep Learning
• D${}_4$CNN$\times$AnaCal: Physics-Informed Machine Learning for Accurate and Precise Weak Lensing Shear Estimation