Mean teacher

Reported on 5 benchmarks across 1 task · 1 paper · 5 SOTA

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

Methodology5 results

Domain AdaptationonUSPS-to-MNIST
Accuracy· 2017-06-16
98.07
best: 98.75 (FAMCD)
SOTA
Self-ensembling for visual domain adaptation arXiv:1706.05208
Domain AdaptationonSVHN-to-MNIST
Accuracy· 2017-06-16
99.18
SOTA
Self-ensembling for visual domain adaptation arXiv:1706.05208
Domain AdaptationonSynth Signs-to-GTSRB
Accuracy· 2017-06-16
98.66
SOTA
Self-ensembling for visual domain adaptation arXiv:1706.05208
Domain AdaptationonVisDA2017
Accuracy· 2017-06-16
85.4
best: 93.8 (FFTAT)
SOTA
Self-ensembling for visual domain adaptation arXiv:1706.05208
Domain AdaptationonMNIST-to-USPS
Accuracy· 2017-06-16
98.26
best: 98.8 (FACT)
SOTA
Self-ensembling for visual domain adaptation arXiv:1706.05208