{
  "abstract": "Aims. The objective of this work is to adapt a deep neural network model to perform galaxy morphological classification trained from crowd annotations, considering the training scheme, the agreement between the annotators, and the hierarchy. Methods. We use Galaxy Zoo 1 as our experimental testbed and trained a convolutional neural network (CNN) for the automatic classification of galaxies' morphologies. We analyze the impact of the following aspects on the classification accuracy and training efficiency: (i) Training only the last layer vs. training all the network; (ii) Classification with only the CNN vs. considering the hierarchy; (iii) Comparing the models trained with different amounts of data and levels of agreement between the annotators; (iv) Training by stages, transferring knowledge from one model to another; and (v) Combining several models as an ensemble. Results From the experiments, we derive the following results: (i) Training all the layers in the network significantly improves the accuracy (10% increase in exact match), compared to training only the last layer; (ii) There is a tradeoff between the amount of data and the level of agreement between the annotators used for training; (iii) Using the hierarchy can improve accuracy when the amount of training data is reduced; (iv) Training by stages through transfer learning (curriculum learning) produces higher accuracy for limited data; (v) Ensembles can improve accuracy; (vi) Models achieve a low accuracy for the most difficult cases, but, if we consider hierarchical measures, we can derive useful results for upper levels in the hierarchy. An accuracy above 99% is achieved when training all layers of the network and considering a high agreement between the annotators. Conclusions. Training deep learning models from crowd annotations involves additional challenges than learning from hard annotations.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.06316",
  "author_total": 3,
  "authors": [
    {
      "name": "Luis Enrique Sucar"
    },
    {
      "name": "Carlos del Burgo"
    },
    {
      "name": "Jonathan Serrano-Pérez"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fw9dbmjpx1zzb.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.06316",
  "fulltext_url": null,
  "id": "fw9dbmjpx1zzb",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.06316",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "astro-ph.GA"
    ],
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "cs.LG"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2609.06316",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-06",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/fw9dbmjpx1zzb.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:15Z",
      "native_id": "2609.06316",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.06316"
    }
  ],
  "subjects": [
    {
      "field": "astronomy",
      "origin": "arxiv:astro-ph.GA",
      "subfield": "galaxies"
    }
  ],
  "title": "Deep learning from the crowd Fundamentals of morphological galaxy classification",
  "title_text": "Deep learning from the crowd Fundamentals of morphological galaxy classification",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:15Z",
  "url": "https://research.draconitic.com/paper/fw9dbmjpx1zzb",
  "venue": "arXiv",
  "versions": [
    {
      "doi": "10.1051/0004-6361/202660502",
      "pid": null,
      "relation": "published-as",
      "title": null,
      "venue": null
    }
  ]
}