CyCleGAN (Light-weight Calibrator)

Reported on 3 benchmarks across 1 task · 1 paper

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

Methodology3 results

Domain AdaptationonUSPS-to-MNIST
Accuracy· 2019-11-28
98.3
best: 98.75 (FAMCD)
Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation arXiv:1911.12796
Domain AdaptationonSVHN-to-MNIST
Accuracy· 2019-11-28
97.5
best: 99.18 (Mean teacher)
Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation arXiv:1911.12796
Domain AdaptationonMNIST-to-USPS
Accuracy· 2019-11-28
97.1
best: 98.8 (FACT)
Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation arXiv:1911.12796