mlsanityData to 14 Oct 2026

Enhanced Meta Label Correction for Coping with Label Corruption

arXiv 2305.12961 ↗First posted 22 May 2023cs.CV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Traditional methods for learning with the presence of noisy labels have successfully handled datasets with artificially injected noise but still fall short of adequately handling real-world noise. With the increasing use of meta-learning in the diverse fields of machine learning, researchers leveraged auxiliary small clean datasets to meta-correct the training labels. Nonetheless, existing meta-label correction approaches are not fully exploiting their potential. In this study, we propose an Enhanced Meta Label Correction approach abbreviated as EMLC for the learning with noisy labels (LNL) problem. We re-examine the meta-learning process and introduce faster and more accurate meta-gradient derivations. We propose a novel teacher architecture tailored explicitly to the LNL problem, equipped with novel training objectives. EMLC outperforms prior approaches and achieves state-of-the-art results in all standard benchmarks. Notably, EMLC enhances the previous art on the noisy real-world dataset Clothing1M by 1.52% while requiring × 0.5 the time per epoch and with much faster convergence of the meta-objective when compared to the baseline approach.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 32 of its 42 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

32 of 42 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  7. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  8. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  9. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  10. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  11. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  12. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
20 more
  1. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
  2. 2020Meta Pseudo Labelscited by 374
  3. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 328
  4. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  5. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  6. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  7. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  8. 2018Learning to Learn from Noisy Labeled Datacited by 160
  9. 2019Deep Self-Learning From Noisy Labelscited by 122
  10. 2019Meta Label Correction for Noisy Label Learningcited by 108
  11. 2021Augmentation Strategies for Learning with Noisy Labelscited by 86
  12. 2015Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameterscited by 71
  13. 2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
  14. 2020Learning to Purify Noisy Labels via Meta Soft Label Correctorcited by 39
  15. 2021Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domainscited by 39
  16. 2021Faster Meta Update Strategy for Noise-Robust Deep Learningcited by 38
  17. 2022Beyond backpropagation: bilevel optimization through implicit differentiation and equilibrium propagationcited by 26
  18. 2020Meta Soft Label Generation for Noisy Labelscited by 21
  19. 2021Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrectioncited by 20
  20. 2023Learning with Noisy labels via Self-supervised Adversarial Noisy Maskingcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025Curvature Learning for Generalization of Hyperbolic Neural Networkscited by 4
  2. 2026FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generationcited by 3
  3. 2025CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy Labelscited by 0
  4. 2026Robust Self-Training with Closed-loop Label Correction for Learning from Noisy Labelscited by 0
  5. 2026Variational Rectification Inference for Learning with Noisy Labelscited by 0
  6. 2026Efficient Bilevel Optimization for Meta Label Correction in Noisy Label Learningcited by 0