Mean Teacher

Reported on 5 benchmarks across 2 tasks · 2 papers · 4 SOTA

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

Computer Vision5 results

Image ClassificationonCIFAR-10, 4000 Labels
Percentage error· 2017-03-06
6.28
best: 3.96 (SimMatch)
SOTA
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results arXiv:1703.01780
Image ClassificationonSVHN, 1000 labels
Accuracy· 2017-03-06
96.05
best: 97.58 (EnAET)
SOTA
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results arXiv:1703.01780
Semi-Supervised Image ClassificationonCIFAR-10, 4000 Labels
Percentage error· 2017-03-06
6.28
best: 3.96 (SimMatch)
SOTA
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results arXiv:1703.01780
Semi-Supervised Image ClassificationonSVHN, 1000 labels
Accuracy· 2017-03-06
96.05
best: 97.58 (EnAET)
SOTA
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results arXiv:1703.01780
Image ClassificationonSTL-10
Percentage correct· 2020-01-21
78.57
best: 99.64 (µ2Net+ (ViT-L/16))
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence arXiv:2001.07685