Workshop — INNS DLIA @ IJCNN — 2023
Morphological Classification of Radio Galaxies using Semi-Supervised Group Equivariant CNNs
Mir Sazzat Hossain, Sugandha Roy, KMB Asad, Arshad Momen, Amin Ahsan Ali, M Ashraful Amin, AKM Mahbubur Rahman
Procedia Computer Science, Volume 222, 2023, Pages 601-612, ISSN 1877-0509.
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.
Topics
Cite
@article{HOSSAIN2023601,
title = {Morphological classification of Radio Galaxies using Semi-Supervised Group Equivariant CNNs},
journal = {Procedia Computer Science},
volume = {222},
pages = {601-612},
year = {2023},
note = {International Neural Network Society Workshop on Deep Learning Innovations and Applications (INNS DLIA 2023)},
issn = {1877-0509},
doi = {https://doi.org/10.1016/j.procs.2023.08.198},
url = {https://www.sciencedirect.com/science/article/pii/S1877050923009638},
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},
keywords = {Radio Galaxy, Fanaroff-Riley, G-CNN, SimCLR, BYOL, Semi-supervised Learning},
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.}
}