PyCDA (ResNet-101)

Reported on 4 benchmarks across 4 tasks · 1 paper · 4 SOTA

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)· 2019-08-26
53.3
best: 74.8 (HRDA + PiPa)
SOTA
Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach arXiv:1908.09547

Methodology1 result

Domain AdaptationonSYNTHIA-to-Cityscapes
mIoU· 2019-08-26
46.7
best: 78.1 (HALO)
SOTA
Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach arXiv:1908.09547

Medical1 result

Image GenerationonSYNTHIA-to-Cityscapes
mIoU (13 classes)· 2019-08-26
53.3
best: 74.8 (HRDA + PiPa)
SOTA
Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach arXiv:1908.09547

Miscellaneous1 result

1 Image, 2*2 StitchingonSYNTHIA-to-Cityscapes
mIoU (13 classes)· 2019-08-26
53.3
best: 74.8 (HRDA + PiPa)
SOTA
Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach arXiv:1908.09547