Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation

Benchmark Model Rank Results
image-to-image-translation-on-synthia-to-cityscapesCPSL#9mIoU (13 classes): 65.3
image-to-image-translation-on-gtav-to-cityscapes-labelsCPSL#15mIoU: 60.8
synthetic-to-real-translation-on-gtav-to-cityscapes-labelsCPSL#22mIoU: 60.8