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

Open paper

Benchmark	Model	Rank	Results
image-to-image-translation-on-gtav-to	CPSL	#12	mIoU: 60.8
image-to-image-translation-on-synthia-to	CPSL	#9	mIoU (13 classes): 65.3
synthetic-to-real-translation-on-gtav-to	CPSL	#18	mIoU: 60.8