Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918513459855360 |
|---|---|
| author | Mao, Jingyang Peng, Ningkang Gu, Yanhui |
| author_facet | Mao, Jingyang Peng, Ningkang Gu, Yanhui |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_20725 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label Mao, Jingyang Peng, Ningkang Gu, Yanhui Computer Vision and Pattern Recognition 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. |
| title | Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.20725 |