DANN [cite:JMLR16RevGrad]

Reported on 2 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.

Methodology1 result

Domain AdaptationonOffice-Home
Accuracy· 2015-05-28
76.8
best: 92.3 (SWG)
SOTA
Domain-Adversarial Training of Neural Networks arXiv:1505.07818

Other1 result

Unsupervised Domain AdaptationonOffice-Home
Accuracy· 2015-05-28
76.8
best: 91.4 (FFTAT)
SOTA
Domain-Adversarial Training of Neural Networks arXiv:1505.07818