mlsanityData to 14 Oct 2026

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

arXiv 2605.20725 ↗First posted 20 May 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 35 references that are in the map. First posted on arXiv 20 May 2026.

Builds on

21 of 35 references.

References · 21

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2020Supervised Contrastive Learningcited by 2,829
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  6. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  7. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  8. 2017A Closer Look at Memorization in Deep Networkscited by 942
  9. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  10. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  11. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
  12. 2019Confident Learning: Estimating Uncertainty in Dataset Labelscited by 413
9 more
  1. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 328
  2. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  3. 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 113
  4. 2020Multi-Objective Interpolation Training for Robustness to Label Noisecited by 86
  5. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  6. 2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
  7. 2021LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environmentcited by 40
  8. 2021Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterioncited by 36
  9. 2023Manifold DivideMix: A Semi-Supervised Contrastive Learning Framework for Severe Label Noisecited by 9

Built on by

Not cited yet.