PITA, a new semi-supervised deep learning algorithm, outperforms prior photo-z methods by using a triple-task loss on images, colors, and available redshifts to produce a smooth latent space.
arXiv preprint arXiv:2405.14930 (2024)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
astro-ph.IM 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Benchmark of Affine, AIM, JetFormer and VQ-VAE tokenizers on galaxy images shows decoupled reconstruction and representation performance with no consistent winner.
Proposes foundation models and decision-theoretic policies to manage evolving source representations and optimize follow-up resource allocation in LSST-scale time-domain astronomy.
citing papers explorer
-
Optimizing Deep Learning Photometric Redshifts for the Roman Space Telescope with HST/CANDELS
PITA, a new semi-supervised deep learning algorithm, outperforms prior photo-z methods by using a triple-task loss on images, colors, and available redshifts to produce a smooth latent space.
-
The Galaxy's Guide to the Tokenizer: A Benchmark for Scientific Foundation Models
Benchmark of Affine, AIM, JetFormer and VQ-VAE tokenizers on galaxy images shows decoupled reconstruction and representation performance with no consistent winner.
-
Toward decision-aware AI for LSST-scale time-domain astronomy
Proposes foundation models and decision-theoretic policies to manage evolving source representations and optimize follow-up resource allocation in LSST-scale time-domain astronomy.