Data-Efficient Classification of Radio Galaxies

TL;DR

This paper demonstrates that high-accuracy classification of radio galaxy morphologies can be achieved with small datasets using deep learning, transfer learning, and few-shot techniques, aiding future large-scale radio surveys.

Contribution

It introduces a novel approach combining few-shot learning and transfer learning for radio galaxy classification on small datasets, achieving over 92% accuracy.

Findings

Achieved over 92% classification accuracy.

Few-shot and transfer learning methods are effective with small datasets.

Confusion mainly occurs between Bent and FRII galaxy types.

Abstract

The continuum emission from radio galaxies can be generally classified into different morphological classes such as FRI, FRII, Bent, or Compact. In this paper, we explore the task of radio galaxy classification based on morphology using deep learning methods with a focus on using a small scale dataset ($\sim 2000$ samples). We apply few-shot learning techniques based on Twin Networks and transfer learning techniques using a pre-trained DenseNet model with advanced techniques like cyclical learning rate and discriminative learning to train the model rapidly. We achieve a classification accuracy of over 92\% using our best performing model with the biggest source of confusion being between Bent and FRII type galaxies. Our results show that focusing on a small but curated dataset along with the use of best practices to train the neural network can lead to good results. Automated classification techniques will be crucial for upcoming surveys with next generation radio telescopes which are expected to detect hundreds of thousands of new radio galaxies in the near future.