RADiff: Controllable Diffusion Models for Radio Astronomical Maps Generation

TL;DR

RADiff introduces a conditional diffusion model to generate synthetic radio astronomical images and annotations, enhancing dataset diversity and improving segmentation performance, thereby addressing data scarcity in radio astronomy.

Contribution

This work presents RADiff, a novel generative model for creating synthetic radio images and annotations to augment datasets and improve deep learning tasks in radio astronomy.

Findings

Synthetic data improved segmentation accuracy by up to 18%.

Generated images from synthetic masks further enhanced model performance.

RADiff can simulate large-scale radio maps for Data Challenges.

Abstract

Along with the nearing completion of the Square Kilometre Array (SKA), comes an increasing demand for accurate and reliable automated solutions to extract valuable information from the vast amount of data it will allow acquiring. Automated source finding is a particularly important task in this context, as it enables the detection and classification of astronomical objects. Deep-learning-based object detection and semantic segmentation models have proven to be suitable for this purpose. However, training such deep networks requires a high volume of labeled data, which is not trivial to obtain in the context of radio astronomy. Since data needs to be manually labeled by experts, this process is not scalable to large dataset sizes, limiting the possibilities of leveraging deep networks to address several tasks. In this work, we propose RADiff, a generative approach based on conditional diffusion models trained over an annotated radio dataset to generate synthetic images, containing radio sources of different morphologies, to augment existing datasets and reduce the problems caused by class imbalances. We also show that it is possible to generate fully-synthetic image-annotation pairs to automatically augment any annotated dataset. We evaluate the effectiveness of this approach by training a semantic segmentation model on a real dataset augmented in two ways: 1) using synthetic images obtained from real masks, and 2) generating images from synthetic semantic masks. We show an improvement in performance when applying augmentation, gaining up to 18% in performance when using real masks and 4% when augmenting with synthetic masks. Finally, we employ this model to generate large-scale radio maps with the objective of simulating Data Challenges.