Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation

Benchmark Model Rank Results
domain-adaptation-on-gta5-to-cityscapesProDA#18mIoU: 57.5
image-to-image-translation-on-gtav-toProDA#13mIoU: 57.5
image-to-image-translation-on-synthia-toProDA#10mIoU (13 classes): 62.0
semantic-segmentation-on-gtav-to-cityscapes-1ProDA#8mIoU: 57.5
synthetic-to-real-translation-on-gtav-toProDA(with knowledge distillation)#22mIoU: 57.5
synthetic-to-real-translation-on-synthia-to-1ProDA(ResNet-101)#14MIoU (16 classes): 55.5MIoU (13 classes): 62.0