Discriminative Patch (ResNet-101)

Reported on 3 benchmarks across 3 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)· 2019-01-16
46.5
best: 74.8 (HRDA + PiPa)
Domain Adaptation for Structured Output via Discriminative Patch Representations arXiv:1901.05427

Medical1 result

Image GenerationonSYNTHIA-to-Cityscapes
mIoU (13 classes)· 2019-01-16
46.5
best: 74.8 (HRDA + PiPa)
Domain Adaptation for Structured Output via Discriminative Patch Representations arXiv:1901.05427

Miscellaneous1 result

1 Image, 2*2 StitchingonSYNTHIA-to-Cityscapes
mIoU (13 classes)· 2019-01-16
46.5
best: 74.8 (HRDA + PiPa)
Domain Adaptation for Structured Output via Discriminative Patch Representations arXiv:1901.05427