PropMix

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Image ClassificationonRed MiniImageNet 20% label noise
Accuracy· 2021-10-22
61.24
best: 69 (NCR (ResNet-18))
SOTA
PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels arXiv:2110.11809
Image ClassificationonRed MiniImageNet 60% label noise
Accuracy· 2021-10-22
52.84
best: 53.21 (InstanceGM-SS)
SOTA
PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels arXiv:2110.11809
Image ClassificationonRed MiniImageNet 40% label noise
Accuracy· 2021-10-22
56.22
best: 64.6 (NCR (ResNet-18))
SOTA
PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels arXiv:2110.11809
Image ClassificationonRed MiniImageNet 80% label noise
Accuracy· 2021-10-22
43.42
best: 51.2 (NCR (ResNet-18))
SOTA
PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels arXiv:2110.11809