| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images | ✓ Link | 81.5% | CurriculumNet | 2018-08-03 |
| Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach | ✓ Link | 80.27 | Forward | 2016-09-13 |
| CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise | ✓ Link | 79.90 | CleanNet w_soft | 2017-11-20 |
| Enhanced Meta Label Correction for Coping with Label Corruption | ✓ Link | 79.35% | EMLC (k=1) | 2023-05-22 |
| Learning from Noisy Labels with Decoupled Meta Label Purifier | ✓ Link | 78.23% | DMLP-DivideMix | 2023-02-14 |
| Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection | ✓ Link | 77.83% | FasTEN | 2021-11-29 |
| Training Classifiers that are Universally Robust to All Label Noise Levels | ✓ Link | 77.70 | PUDistill | 2021-05-27 |
| L2B: Learning to Bootstrap Robust Models for Combating Label Noise | ✓ Link | 77.5 ± 0.2% | L2B (ResNet-18) | 2022-02-09 |
| Meta Label Correction for Noisy Label Learning | ✓ Link | 75.78% | MLC | 2019-11-10 |