Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation

Benchmark Model Rank Results
semi-supervised-semantic-segmentation-on-1CPCL (DeepLab v3+ with ResNet-50)#18Validation mIoU: 76.98%
semi-supervised-semantic-segmentation-on-15CPCL (DeepLab v3+ with ResNet-101)#7Validation mIoU: 77.67%
semi-supervised-semantic-segmentation-on-15CPCL (DeepLab v3+ with ResNet-50)#10Validation mIoU: 75.3%
semi-supervised-semantic-segmentation-on-2CPCL (DeepLab v3+ with ResNet-50)#17Validation mIoU: 74.6%
semi-supervised-semantic-segmentation-on-21CPCL (DeepLab v3+ with ResNet-101)#13Validation mIoU: 73.44
semi-supervised-semantic-segmentation-on-21CPCL (DeepLab v3+ with ResNet-50)#14Validation mIoU: 71.66
semi-supervised-semantic-segmentation-on-22CPCL (DeepLab v3+ with ResNet-50)#16Validation mIoU: 69.92%
semi-supervised-semantic-segmentation-on-27CPCL (DeepLab v3+ with ResNet-50)#16Validation mIoU: 61.88
semi-supervised-semantic-segmentation-on-28CPCL (DeepLab v3+ with ResNet-50)#15Validation mIoU: 67.02
semi-supervised-semantic-segmentation-on-29CPCL (DeepLab v3+ with ResNet-50)#13Validation mIoU: 72.14
semi-supervised-semantic-segmentation-on-30CPCL (DeepLab v3+ with ResNet-50)#15Validation mIoU: 74.25
semi-supervised-semantic-segmentation-on-4CPCL (DeepLab v3+ with ResNet-101)#16Validation mIoU: 76.4%
semi-supervised-semantic-segmentation-on-4CPCL (DeepLab v3+ with ResNet-50)#21Validation mIoU: 73.74%
semi-supervised-semantic-segmentation-on-8CPCL (DeepLab v3+ with ResNet-50)#17Validation mIoU: 78.17%
semi-supervised-semantic-segmentation-on-9CPCL (DeepLab v3+ with ResNet-101)#16Validation mIoU: 77.16
semi-supervised-semantic-segmentation-on-9CPCL (DeepLab v3+ with ResNet-50)#22Validation mIoU: 74.58