# Transfer learning for radio galaxy classification

## TL;DR

This paper explores transfer learning with deep neural networks for radio galaxy classification across different surveys, demonstrating how pre-trained models can improve or impair classification performance depending on the survey combination.

## Contribution

It introduces a transfer learning approach for radio galaxy classification using a 13-layer DCNN, analyzing cross-survey model adaptation and its implications for future radio surveys.

## Key findings

- Pre-trained models on FIRST improve NVSS classification performance.
- Pre-trained models on NVSS do not enhance FIRST classification.
- Transfer learning effectiveness depends on survey data resolution and characteristics.

## Abstract

In the context of radio galaxy classification, most state-of-the-art neural network algorithms have been focused on single survey data. The question of whether these trained algorithms have cross-survey identification ability or can be adapted to develop classification networks for future surveys is still unclear. One possible solution to address this issue is transfer learning, which re-uses elements of existing machine learning models for different applications. Here we present radio galaxy classification based on a 13-layer Deep Convolutional Neural Network (DCNN) using transfer learning methods between different radio surveys. We find that our machine learning models trained from a random initialization achieve accuracies comparable to those found elsewhere in the literature. When using transfer learning methods, we find that inheriting model weights pre-trained on FIRST images can boost model performance when re-training on lower resolution NVSS data, but that inheriting pre-trained model weights from NVSS and re-training on FIRST data impairs the performance of the classifier. We consider the implication of these results in the context of future radio surveys planned for next-generation radio telescopes such as ASKAP, MeerKAT, and SKA1-MID.