A Multimodal Dataset and Benchmark for Radio Galaxy and Infrared Host Detection

Abstract

We present a novel multimodal dataset developed by expert astronomers to automate the detection and localisation of multi-component extended radio galaxies and their corresponding infrared hosts. The dataset comprises 4,155 instances of galaxies in 2,800 images with both radio and infrared modalities. Each instance contains information on the extended radio galaxy class, its corresponding bounding box that encompasses all of its components, pixel-level segmentation mask, and the position of its corresponding infrared host galaxy. Our dataset is the first publicly accessible dataset that includes images from a highly sensitive radio telescope, infrared satellite, and instance-level annotations for their identification. We benchmark several object detection algorithms on the dataset and propose a novel multimodal approach to identify radio galaxies and the positions of infrared hosts simultaneously.

Accepted in NeurIPS 2023 conference ML4PS workshop (https://nips.cc/). The full version accepted in PASA, is available at https://doi.org/10.1017/pasa.2023.64

References in corpus (11)

• DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
• Cataloging the radio-sky with unsupervised machine learning: a new approach for the SKA era
• CNN Architecture Comparison for Radio Galaxy Classification
• Unveiling the rarest morphologies of the LOFAR Two-metre Sky Survey radio source population with self-organised maps
• Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks
• Attention-gating for improved radio galaxy classification
• Odd Radio Circles and their Environment
• Morphological classification of compact and extended radio galaxies using convolutional neural networks and data augmentation techniques
• Artificial intelligence for celestial object census: the latest technology meets the oldest science
• A Multimodal Dataset and Benchmark for Radio Galaxy and Infrared Host Detection
• Feature Guided Training and Rotational Standardisation for the Morphological Classification of Radio Galaxies

Cited by in corpus (9)

• A Multimodal Dataset and Benchmark for Radio Galaxy and Infrared Host Detection
• YOLO-CIANNA: Galaxy detection with deep learning in radio data. I. A new YOLO-inspired source detection method applied to the SKAO SDC1
• The SARAO MeerKAT Galactic Plane Survey extended source catalogue
• Identification of 4876 Bent-Tail Radio Galaxies in the FIRST Survey Using Deep Learning Combined with Visual Inspection
• Discovery of Odd Radio Circles and Other Peculiars in the First Year of the EMU Survey using Object Detection
• Self-Supervised Learning on MeerKAT Wide-Field Continuum Images
• Deep learning-based astronomical multimodal data fusion: A comprehensive review
• EMU and the DRAGNs I: A Catalogue of DRAGNs
• Quantifying Radio Source Morphology