A dual-network asymmetric co-teaching framework trained on injected transients and contaminated survey data achieves human-label-free real-bogus classification with calibrated uncertainty.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.IM 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification
A dual-network asymmetric co-teaching framework trained on injected transients and contaminated survey data achieves human-label-free real-bogus classification with calibrated uncertainty.