Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization
Open paper
Benchmark
Model
Rank
Results
synthetic-to-real-translation-on-gtav-to
Coarse-to-Fine
–
mIoU: 56.1
synthetic-to-real-translation-on-synthia-to-1
Coarse-to-Fine(ResNet-101)
–
MIoU (16 classes): 48.2
MIoU (13 classes): 55.5
Rank counts only results with a code link.