A Multimodal Dataset and Benchmark for Radio Galaxy and Infrared Host Detection
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.
Code (3)
Tasks
object-detectionObject DetectionPositionSimilar Papers 제목 키워드 기반
RadioGalaxyNET: Dataset and Novel Computer Vision Algorithms for the Detection of Extended Radio Galaxies and Infrared Hosts
Creating radio galaxy catalogues from next-generation deep surveys requires automated identification of associated components of extended sources and their corresponding infrared hosts. In this paper, we introduce RadioG…
2D Object Detectionobject-detectionObject DetectionPathfinderSpectral Energy Distributions of Hard X-ray selected AGNs in the XMDS Survey
We present the spectral energy distributions (SEDs) of a hard X-ray selected sample. The sample contains 136 sources with F(2-10 keV)>10^-14 erg/cm^2/s and 132 are AGNs. The sources are detected in a 1 square degree area…
RGC-Bent: A Novel Dataset for Bent Radio Galaxy Classification
We introduce a novel machine learning dataset tailored for the classification of bent radio active galactic nuclei (AGN) in astronomical observations. Bent radio AGN, distinguished by their curved jet structures, provide…
AstronomyClassificationDeep Learning for Morphological Identification of Extended Radio Galaxies using Weak Labels
The present work discusses the use of a weakly-supervised deep learning algorithm that reduces the cost of labelling pixel-level masks for complex radio galaxies with multiple components. The algorithm is trained on weak…
Instance SegmentationPathfinderSemantic SegmentationAnomaly detection in radio galaxy data with trainable COSFIRE filters
Detecting anomalies in radio astronomy is challenging due to the vast amounts of data and the rarity of labeled anomalous examples. Addressing this challenge requires efficient methods capable of identifying unusual radi…
Anomaly DetectionAstronomy