2023
Hossain, Mir Sazzat; Roy, Sugandha; Asad, K. M. B.; Momen, Arshad; Ali, Amin Ahsan; Amin, M Ashraful; Rahman, A. K. M. Mahbubur
Morphological classification of Radio Galaxies using Semi-Supervised Group Equivariant CNNs Journal Article
In: Procedia Computer Science, vol. 222, pp. 601-612, 2023, ISSN: 1877-0509, (International Neural Network Society Workshop on Deep Learning Innovations and Applications (INNS DLIA 2023)).
Abstract | Links | BibTeX | Tags: BYOL, Fanaroff-Riley, G-CNN, Radio Galaxy, Semi-supervised Learning, SimCLR
@article{HOSSAIN2023601,
title = {Morphological classification of Radio Galaxies using Semi-Supervised Group Equivariant CNNs},
author = {Mir Sazzat Hossain and Sugandha Roy and K. M. B. Asad and Arshad Momen and Amin Ahsan Ali and M Ashraful Amin and A. K. M. Mahbubur Rahman},
url = {https://www.sciencedirect.com/science/article/pii/S1877050923009638},
doi = {https://doi.org/10.1016/j.procs.2023.08.198},
issn = {1877-0509},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {Procedia Computer Science},
volume = {222},
pages = {601-612},
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.},
note = {International Neural Network Society Workshop on Deep Learning Innovations and Applications (INNS DLIA 2023)},
keywords = {BYOL, Fanaroff-Riley, G-CNN, Radio Galaxy, Semi-supervised Learning, SimCLR},
pubstate = {published},
tppubtype = {article}
}
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.
