Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training

Benchmark Model Rank Results
image-to-image-translation-on-gtav-toCBST#16mIoU: 47.0
semi-supervised-semantic-segmentation-on-23CBST (Range View)#6mIoU (1% Labels): 35.7mIoU (10% Labels): 50.7mIoU (20% Labels): 52.7
semi-supervised-semantic-segmentation-on-24CBST (Range View)#7mIoU (1% Labels): 39.9mIoU (10% Labels): 53.4mIoU (20% Labels): 56.1
semi-supervised-semantic-segmentation-on-25CBST (Range View)#9mIoU (1% Labels): 40.9mIoU (10% Labels): 60.5mIoU (20% Labels): 64.3