DANN [ganin2016domain]

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

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

Methodology3 results

Domain AdaptationonMNIST-to-MNIST-M
Accuracy· 2015-05-28
77.4
best: 98.7 (DRANet)
SOTA
Domain-Adversarial Training of Neural Networks arXiv:1505.07818
Domain AdaptationonSynth Digits-to-SVHN
Accuracy· 2015-05-28
90.3
best: 91.2 (DSN (DANN))
SOTA
Domain-Adversarial Training of Neural Networks arXiv:1505.07818
Domain AdaptationonSVNH-to-MNIST
Accuracy· 2015-05-28
70.7
best: 98.91 (SRDA (RAN))
Domain-Adversarial Training of Neural Networks arXiv:1505.07818