| Paper | Code | Accuracy (under 20% Sym. label noise) | Accuracy (under 50% Sym. label noise) | Accuracy (under 80% Sym. label noise) | Accuracy (under 90% Sym. label noise) | Accuracy (under 95% Sym. label noise) | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|
| SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise | ✓ Link | 96.74% | 96.13% | 95.56% | 95.17% | SSR | 2021-11-22 | |
| Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels | ✓ Link | 96.74 ± 0.12 | 95.55 ± 0.32 | 93.11 ± 0.70 | 89.30 ± 0.21 | 80.21 ± 1.91 | C2D (ELR+ with SimCLR, ResNet-34) | 2021-03-25 |
| Sample Prior Guided Robust Model Learning to Suppress Noisy Labels | ✓ Link | 96.7% | 96.3% | 94.7% | 84.0% | PGDF (ResNet-18) | 2021-12-02 | |
| Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels | ✓ Link | 96.23 ± 0.09 | 95.15 ± 0.16 | 94.30 ± 0.12 | 93.42 ± 0.09 | 87.72 ± 2.21 | C2D (DivideMix with SimCLR, ResNet-18) | 2021-03-25 |