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

ArXi:2605.20725v1 Announce Type: new 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 cons