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.
, archivePrefix = "arXiv", eprint =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
CO observations of the COSMOS-Gr30 group at z~0.7 show average molecular gas contents reduced by 0.5 dex relative to field galaxies, with gas fractions 20-40% of main-sequence values, plus an upper limit on cold gas in the extended ionized structure.
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.
-
Probing the molecular gas content of galaxies in an over-dense group at z~0.7: a test case for environmental quenching
CO observations of the COSMOS-Gr30 group at z~0.7 show average molecular gas contents reduced by 0.5 dex relative to field galaxies, with gas fractions 20-40% of main-sequence values, plus an upper limit on cold gas in the extended ionized structure.