Review
Jul 2026
Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification
The results show that injection-driven, weakly supervised training can enable scalable and consistent Real-Bogus classification without human-labeled training data while providing calibrated uncertainties, and achieves competitive calibration relative to more expensive ensemble baselines.
Raphaël Bonnet-Guerrini, B. S'anchez, D. Fouchez et al.
· 1 citation