Related papers: Morphological Classification of Radio Galaxies using Semi-Supervised Group Equivariant CNNs

Morphological Classification of Radio Galaxies using Semi-Supervised Group Equivariant CNNs

URL: http://arxiv.org/abs/2306.00031v1
Date: Wed, 31 May 2023 06:50:32 GMT
Title: Morphological Classification of Radio Galaxies using Semi-Supervised Group Equivariant CNNs
Authors: Mir Sazzat Hossain (1), Sugandha Roy (1), K. M. B. Asad (1 and 2 and 3), Arshad Momen (1 and 2), Amin Ahsan Ali (1), M Ashraful Amin (1), A. K. M. Mahbubur Rahman (1) ((1) Center for Computational & Data Sciences, Independent University, Bangladesh, (2) Department of Physical Sciences, Independent University, Bangladesh, (3) Astronomy and Radio Research Group, SETS, Independent University, Bangladesh)
Abstract summary: Out of the estimated few trillion galaxies, only around a million have been detected through radio frequencies. We employ a semi-supervised learning approach to classify them into the known Fanaroff-Riley Type I (FRI) and Type II (FRII) categories. A Group Equivariant Convolutional Neural Network (G-CNN) was used as an encoder of the state-of-the-art self-supervised methods SimCLR and BYOL.
Score: 0.0
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Out of the estimated few trillion galaxies, only around a million have been detected through radio frequencies, and only a tiny fraction, approximately a thousand, have been manually classified. We have addressed this disparity between labeled and unlabeled images of radio galaxies by employing a semi-supervised learning approach to classify them into the known Fanaroff-Riley Type I (FRI) and Type II (FRII) categories. A Group Equivariant Convolutional Neural Network (G-CNN) was used as an encoder of the state-of-the-art self-supervised methods SimCLR (A Simple Framework for Contrastive Learning of Visual Representations) and BYOL (Bootstrap Your Own Latent). The G-CNN preserves the equivariance for the Euclidean Group E(2), enabling it to effectively learn the representation of globally oriented feature maps. After representation learning, we trained a fully-connected classifier and fine-tuned the trained encoder with labeled data. Our findings demonstrate that our semi-supervised approach outperforms existing state-of-the-art methods across several metrics, including cluster quality, convergence rate, accuracy, precision, recall, and the F1-score. Moreover, statistical significance testing via a t-test revealed that our method surpasses the performance of a fully supervised G-CNN. This study emphasizes the importance of semi-supervised learning in radio galaxy classification, where labeled data are still scarce, but the prospects for discovery are immense.