Combining astrophysical datasets with CRUMB

Porter, Fiona A. M. and Scaife, Anna M. M. (2023) Combining astrophysical datasets with CRUMB. In: Advances in Neural Information Processing Systems, 2023-12-10 - 2023-12-16.

[thumbnail of Porter-Scaife-2023-Combining-astrophysical-datasets-with-CRUMB]
Preview
 Text. Filename: Porter-Scaife-2023-Combining-astrophysical-datasets-with-CRUMB.pdf
Accepted Author Manuscript
License: Strathprints license 1.0
Download (820kB)| Preview

Abstract

At present, the field of astronomical machine learning lacks widely-used benchmarking datasets; most research employs custom-made datasets which are often not publicly released, making comparisons between models difficult. In this paper we present CRUMB, a publicly-available image dataset of Fanaroff-Riley galaxies constructed from four "parent" datasets extant in the literature. In addition to providing the largest image dataset of these galaxies, CRUMB uses a two-tier labelling system: a "basic" label for classification and a "complete" label which provides the original class labels used in the four parent datasets, allowing for disagreements in an image's class between different datasets to be preserved and selective access to sources from any desired combination of the parent datasets.

ORCID iDs

Porter, Fiona A. M. ORCID logoORCID: https://orcid.org/0000-0002-5695-0633 and Scaife, Anna M. M.;
  • Item type:Conference or Workshop Item(Paper)
    ID code:90280
    Dates:
    Date
    Event
    17 November 2023
    Published
    Notes:Accepted in Machine Learning and the Physical Sciences Workshop at NeurIPS 2023; 6 pages, 1 figure, 1 table
    Subjects:Science > Physics
    Department:UNSPECIFIED
    Depositing user: Pure Administrator
    Date deposited:16 Aug 2024 14:01
    Last modified:22 Sep 2024 00:34
    Related URLs:
    URI:https://strathprints.strath.ac.uk/id/eprint/90280
CORE (COnnecting REpositories)