HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation

Open paper
Benchmark Model Rank Results
image-to-image-translation-on-synthia-to-cityscapesHRDA#3mIoU (13 classes): 72.4
image-to-image-translation-on-gtav-to-cityscapes-labelsHRDA#5mIoU: 73.8
semantic-segmentation-on-gtav-to-cityscapes-labelsHRDA#5mIoU: 73.8
unsupervised-domain-adaptation-on-synthia-to-cityscapesHRDA#5mIoU (13 classes): 72.4mIoU: 65.8
semantic-segmentation-on-dark-zurichHRDA#6mIoU: 55.9
semantic-segmentation-on-synthia-to-cityscapesHRDA#6Mean IoU: 65.8
unsupervised-domain-adaptation-on-gtav-to-cityscapes-labelsHRDA#6mIoU: 73.8
domain-adaptation-on-cityscapes-to-acdcHRDA#7mIoU: 68.0
synthetic-to-real-translation-on-gtav-to-cityscapes-labelsHRDA#7mIoU: 73.8
domain-adaptation-on-gta5-to-cityscapesHRDA#8mIoU: 73.8
synthetic-to-real-translation-on-synthia-to-cityscapesHRDA#8MIoU (16 classes): 65.8MIoU (13 classes): 72.4
domain-adaptation-on-synthia-to-cityscapesHRDA#10mIoU: 65.8

Rank counts only results with a code link.