| semi-supervised-semantic-segmentation-on-cityscapes-100-samples-labeled | ReCo (DeepLab v3+ with ResNet-101 backbone, ImageNet pretrained) | #6 | Validation mIoU: 60.28% |
| semi-supervised-semantic-segmentation-on-cityscapes-100-samples-labeled | ReCo (DeepLab v2 with ResNet-101 backbone, ImageNet pretrained) | #9 | Validation mIoU: 56.53% |
| semi-supervised-semantic-segmentation-on-cityscapes-12-5-labeled | ReCo (DeepLab v3+ with ResNet-101 backbone, ImageNet pretrained) | #23 | Validation mIoU: 66.44% |
| semi-supervised-semantic-segmentation-on-cityscapes-12-5-labeled | ReCo (DeepLab v2 with ResNet-101 backbone, ImageNet pretrained) | #25 | Validation mIoU: 64.94% |
| semi-supervised-semantic-segmentation-on-cityscapes-25-labeled | ReCo (DeepLab v3+ with ResNet-101 backbone, ImageNet pretrained) | #21 | Validation mIoU: 68.50% |
| semi-supervised-semantic-segmentation-on-cityscapes-25-labeled | ReCo (DeepLab v2 with ResNet-101 backbone, ImageNet pretrained) | #22 | Validation mIoU: 67.53% |
| semi-supervised-semantic-segmentation-on-cityscapes-50-labeled | ReCo (DeepLab v2 with ResNet-101 backbone, ImageNet pretrained) | #20 | Validation mIoU: 68.69% |
| semi-supervised-semantic-segmentation-on-pascal-voc-2012-1-labeled | ReCo (DeepLab v3+ with ResNet-101 backbone, ImageNet pre-trained) | #1 | Validation mIoU: 63.60% |
| semi-supervised-semantic-segmentation-on-pascal-voc-2012-1-labeled | ReCo (DeepLab v2 with ResNet-101 backbone, ImageNet pre-trained) | #2 | Validation mIoU: 63.16% |
| semi-supervised-semantic-segmentation-on-pascal-voc-2012-12-5-labeled | ReCo | #29 | Validation mIoU: 71.00% |
| semi-supervised-semantic-segmentation-on-pascal-voc-2012-2-labeled | ReCo (DeepLab v3+ with ResNet-101 backbone, ImageNet pretrained) | #1 | Validation mIoU: 72.14% |
| semi-supervised-semantic-segmentation-on-pascal-voc-2012-2-labeled | ReCo (DeepLab v2 with ResNet-101 backbone, ImageNet pretrained) | #5 | Validation mIoU: 66.41% |
| semi-supervised-semantic-segmentation-on-pascal-voc-2012-5-labeled | ReCo (DeepLab v3+ with ResNet-101 backbone, ImageNet pretrained) | #1 | Validation mIoU: 73.66% |
| semi-supervised-semantic-segmentation-on-pascal-voc-2012-5-labeled | ReCo (DeepLab v2 with ResNet-101 backbone, ImageNet pretrained) | #7 | Validation mIoU: 68.85% |