Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization

Benchmark Model Rank Results
synthetic-to-real-translation-on-gtav-to-cityscapes-labelsCoarse-to-Fine–mIoU: 56.1
synthetic-to-real-translation-on-synthia-to-cityscapesCoarse-to-Fine(ResNet-101)–MIoU (16 classes): 48.2MIoU (13 classes): 55.5