UPS (CNN-13)

Reported on 6 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision6 results

Image ClassificationonCIFAR-100, 4000 Labels
Accuracy· 2021-01-15
59.23
SOTA
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning arXiv:2101.06329
Semi-Supervised Image ClassificationonCIFAR-100, 4000 Labels
Accuracy· 2021-01-15
59.23
SOTA
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning arXiv:2101.06329
Image ClassificationonCIFAR-10, 1000 Labels
Accuracy· 2021-01-15
91.82
best: 92.25 (MixMatch)
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning arXiv:2101.06329
Image Classificationoncifar-100, 10000 Labels
Percentage error· 2021-01-15
32
best: 19.32 (CCSSL(FixMatch))
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning arXiv:2101.06329
Semi-Supervised Image ClassificationonCIFAR-10, 1000 Labels
Accuracy· 2021-01-15
91.82
best: 92.25 (MixMatch)
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning arXiv:2101.06329
Semi-Supervised Image Classificationoncifar-100, 10000 Labels
Percentage error· 2021-01-15
32
best: 19.32 (CCSSL(FixMatch))
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning arXiv:2101.06329