Metraipolis › archive › dc_b0170fcfb900

Galaxy Morphology Classification: Uncertainty Modeling and Out of Distribution Detection — arXiv:2608.16654

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16654
License (as archived)
CC0-1.0
Archived
2026-10-19T01:54:53.193Z
SHA-256 of the archived text
34a8046fe65d221bea4809c0951aa86c19a461b83422b444cedb77445a2edeb3
Stable URL of this page
https://metraipolis.com/documento/dc_b0170fcfb900

How to cite

Galaxy Morphology Classification: Uncertainty Modeling and Out of Distribution Detection — arXiv:2608.16654 — arXiv (en), https://arxiv.org/abs/2608.16654 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b0170fcfb900 (Metraipolis archive dc_b0170fcfb900, sha256 34a8046fe65d221bea4809c0951aa86c19a461b83422b444cedb77445a2edeb3)
BibTeX
@misc{dcb0170fcfb900,
  title = {Galaxy Morphology Classification: Uncertainty Modeling and Out of Distribution Detection — arXiv:2608.16654},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16654},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b0170fcfb900; sha256 34a8046fe65d221bea4809c0951aa86c19a461b83422b444cedb77445a2edeb3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16654. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present a comprehensive framework for galaxy morphology classification that combines enhanced ``out-of-distribution (OOD)'' detection with improved uncertainty quantification. Using ``Galaxy Zoo DECaLS'', we trained a ResNet-34 architecture under three configurations: standard cross-entropy loss as a baseline, IsoMaxPlus loss function for OOD detection, and hybrid IsoMaxPlus+MonteCarlo Dropout for enhanced uncertainty quantification. IsoMaxPlus replaces the conventional SoftMax logits with distance-based class representations, preserving inter-class separability and enabling reliable OOD detection, without requiring additional architectural modifications or hyperparameter tuning. Coalescing IsoMaxPlus with MC Dropout provides a fast Bayesian approximation by performing multiple stochastic forward passes during inference. Our results show that IsoMaxPlus substantially improves OOD detection, increasing TNR@TPR95 by nearly $90\%$ relative to the cross-entropy baseline, while maintaining a competitive accuracy of 97\% across nine morphological classes. Additionally, with MC Dropout, the model yields more stable predictions and a reduction in calibration error, providing more reliable uncertainty estimates. The Expected Calibration Error (ECE) is reduced from $0.0095$ to $0.0026$ ($\approx73\%$) for IsoMaxPlus and $0.0033$ ($\approx65\%$) when combined with MC Dropout, compared to the baseline. Misclassified or underconfident predictions exhibit higher predictive entropy and lower minimum distance scores, providing an interpretable metric for identifying unreliable predictions. These methods are well-suited for current and upcoming large-scale surveys, where reliable automated morphological classification and awareness of uncertainty are essential for identifying rare or previously unseen galaxy morphologies.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-08-18 in astro-ph.IM).
Categorie arXiv: Instrumentation and Methods for Astrophysics (astro-ph.IM).
Pagina del lavoro: https://arxiv.org/abs/2608.16654 — 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 2026-10-19T01:01:05.968Z dalla pagina https://arxiv.org/catchup/astro-ph.IM/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).