Attention-gating for improved radio galaxy classification

Abstract

In this work we introduce attention as a state of the art mechanism for classification of radio galaxies using convolutional neural networks. We present an attention-based model that performs on par with previous classifiers while using more than 50% fewer parameters than the next smallest classic CNN application in this field. We demonstrate quantitatively how the selection of normalisation and aggregation methods used in attention-gating can affect the output of individual models, and show that the resulting attention maps can be used to interpret the classification choices made by the model. We observe that the salient regions identified by the our model align well with the regions an expert human classifier would attend to make equivalent classifications. We show that while the selection of normalisation and aggregation may only minimally affect the performance of individual models, it can significantly affect the interpretability of the respective attention maps and by selecting a model which aligns well with how astronomers classify radio sources by eye, a user can employ the model in a more effective manner.

18 pages, 16 figures, Published in MNRAS

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• The Gaia mission
• Multiple Object Recognition with Visual Attention
• 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)
• A pilot study of the radio-emitting AGN population: the emerging new class of FR0 radio-galaxies
• Classifying Radio Galaxies with Convolutional Neural Network
• The cosmic evolution of radio-AGN feedback to z=1
• FRICAT: A FIRST catalog of FRI radio galaxies
• Morphological classification of radio galaxies: Capsule Networks versus Convolutional Neural Networks
• Radio Galaxy Zoo: A Search for Hybrid Morphology Radio Galaxies
• On the population of remnant FRII radio galaxies and implications for radio source dynamics
• Science with the Murchison Widefield Array: Phase I Results and Phase II Opportunities
• The Combined NVSS-FIRST Galaxies (CoNFIG) Sample - I. Sample Definition, Classification and Evolution

Cited by in corpus (1)

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