Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification
Time-domain surveys generate many transient candidates, making Real-Bogus classification a critical step in automated discovery pipelines. Reliable labels are costly, while community labels can be noisy and survey-dependent. We aim to develop a Real-Bogus classification framework that can be trained without human-labeled data using injected transients and bogus-dominated survey data, remains robust under strong class contamination, and provides calibrated uncertainty quantification. We combine simulated transient injections with a contaminated survey class and train a dual-network model using
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorRaphaël Bonnet-Guerrini →
Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification
- Linked via arxiv authorBruno Sanchez →
Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification
- Linked via arxiv authorDominique Fouchez →
Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification
- Linked via arxiv authorBenjamin Racine →
Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification
- Linked via arxiv authorMaya Guy →
Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification
- Linked via arxiv authorMariam Sabalbal →
Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification
- Linked via arxiv authorManal Yassine →
Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification
- Linked via arxiv authorVincenzo Piuri →
Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification