Metraipolis › archive › dc_4ac1b4d192fb

Deep learning from the crowd Fundamentals of morphological galaxy classification — arXiv:2609.06316

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06316
License (as archived)
CC0-1.0
Archived
2026-10-16T13:58:54.974Z
SHA-256 of the archived text
54af32eaf50a592e37c107b9a2b48fd3eaa4af64e120888d11f73a2101f9f6e5
Stable URL of this page
https://metraipolis.com/documento/dc_4ac1b4d192fb

How to cite

Deep learning from the crowd Fundamentals of morphological galaxy classification — arXiv:2609.06316 — arXiv (en), https://arxiv.org/abs/2609.06316 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4ac1b4d192fb (Metraipolis archive dc_4ac1b4d192fb, sha256 54af32eaf50a592e37c107b9a2b48fd3eaa4af64e120888d11f73a2101f9f6e5)
BibTeX
@misc{dc4ac1b4d192fb,
  title = {Deep learning from the crowd Fundamentals of morphological galaxy classification — arXiv:2609.06316},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06316},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4ac1b4d192fb; sha256 54af32eaf50a592e37c107b9a2b48fd3eaa4af64e120888d11f73a2101f9f6e5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06316. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Astrophysics of Galaxies (astro-ph.GA) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.06316 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T13:39:43.161Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).