Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label

Le résumé fourni par la source

Learning with noisy labels in multimedia classification often combines external annotations and model predictions into a single reliability weight, even though the two sources can fail for different reasons. We instead estimate disentangled reliabilities: bilevel meta-learning produces two batch-normalized scalars per sample, alpha for the given label and beta for the pseudo-label, without constraining them to sum to one. Holistic Reliability Propagation (HRP) then routes them to different objectives, using reliability-aware Mixup with global gating on the input branch and beta-gated pseudo-label positives on the contrastive branch. On synthetic and real-world benchmarks, HRP improves average accuracy over strong baselines and remains competitive at the highest noise rates.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.