DebiasPL (w/ FixMatch)

Reported on 4 benchmarks across 2 tasks · 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 ClassificationonCIFAR-10, 40 Labels
Percentage error· 2022-01-05
5.4
best: 3.51 (SemiOccam)
SOTA
Debiased Learning from Naturally Imbalanced Pseudo-Labels arXiv:2201.01490
Image ClassificationonCIFAR-10, 250 Labels
Percentage error· 2022-01-05
4.6
best: 3.47 (SemiOccam)
SOTA
Debiased Learning from Naturally Imbalanced Pseudo-Labels arXiv:2201.01490
Semi-Supervised Image ClassificationonCIFAR-10, 40 Labels
Percentage error· 2022-01-05
5.4
best: 3.51 (SemiOccam)
SOTA
Debiased Learning from Naturally Imbalanced Pseudo-Labels arXiv:2201.01490
Semi-Supervised Image ClassificationonCIFAR-10, 250 Labels
Percentage error· 2022-01-05
4.6
best: 3.47 (SemiOccam)
SOTA
Debiased Learning from Naturally Imbalanced Pseudo-Labels arXiv:2201.01490