Dual Student (600)

Reported on 6 benchmarks across 2 tasks · 1 paper

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

Computer Vision6 results

Image ClassificationonCIFAR-10, 4000 Labels
Percentage error· 2019-09-03
8.89
best: 3.96 (SimMatch)
Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning arXiv:1909.01804
Image ClassificationonCIFAR-10, 2000 Labels
Accuracy· 2019-09-03
89.28
best: 92.97 (MixMatch)
Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning arXiv:1909.01804
Image ClassificationonCIFAR-10, 1000 Labels
Accuracy· 2019-09-03
85.83
best: 92.25 (MixMatch)
Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning arXiv:1909.01804
Semi-Supervised Image ClassificationonCIFAR-10, 4000 Labels
Percentage error· 2019-09-03
8.89
best: 3.96 (SimMatch)
Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning arXiv:1909.01804
Semi-Supervised Image ClassificationonCIFAR-10, 2000 Labels
Accuracy· 2019-09-03
89.28
best: 92.97 (MixMatch)
Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning arXiv:1909.01804
Semi-Supervised Image ClassificationonCIFAR-10, 1000 Labels
Accuracy· 2019-09-03
85.83
best: 92.25 (MixMatch)
Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning arXiv:1909.01804