FADA (ResNet-101)

Reported on 4 benchmarks across 4 tasks · 1 paper

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

Computer Vision1 result

Image-to-Image TranslationonSYNTHIA-to-Cityscapes
mIoU (13 classes)· 2020-07-17
52.5
best: 74.8 (HRDA + PiPa)
Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation arXiv:2007.09222

Methodology1 result

Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU· 2020-07-17
45.2
best: 78.1 (HALO)
Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation arXiv:2007.09222

Medical1 result

Image GenerationonSYNTHIA-to-Cityscapes
mIoU (13 classes)· 2020-07-17
52.5
best: 74.8 (HRDA + PiPa)
Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation arXiv:2007.09222

Miscellaneous1 result

1 Image, 2*2 StitchingonSYNTHIA-to-Cityscapes
mIoU (13 classes)· 2020-07-17
52.5
best: 74.8 (HRDA + PiPa)
Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation arXiv:2007.09222