UNet (real)

Reported on 4 benchmarks across 2 tasks · 1 paper

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

Computer Vision2 results

Scene ParsingonHelen
Mean F1· 2021-09-30
91.6
best: 93.8 (DML-CSR)
Fake It Till You Make It: Face analysis in the wild using synthetic data alone arXiv:2109.15102
Scene ParsingonLaPa
Mean F1· 2021-09-30
90.9
best: 93.88 (FaRL-B)
Fake It Till You Make It: Face analysis in the wild using synthetic data alone arXiv:2109.15102

Audio2 results

2D Semantic SegmentationonHelen
Mean F1· 2021-09-30
91.6
best: 93.8 (DML-CSR)
Fake It Till You Make It: Face analysis in the wild using synthetic data alone arXiv:2109.15102
2D Semantic SegmentationonLaPa
Mean F1· 2021-09-30
90.9
best: 93.88 (FaRL-B)
Fake It Till You Make It: Face analysis in the wild using synthetic data alone arXiv:2109.15102