Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation

Open paper
Benchmark Model Rank Results
semi-supervised-semantic-segmentation-on-1CW-BASS (DeepLab v3+ with ResNet-50)#13Validation mIoU: 78.43%
semi-supervised-semantic-segmentation-on-2CW-BASS (DeepLab v3+ with ResNet-50)#12Validation mIoU: 77.20%
semi-supervised-semantic-segmentation-on-22CW-BASS (DeepLab v3+ with ResNet-50)#11Validation mIoU: 75.00
semi-supervised-semantic-segmentation-on-27CW-BASS (DeepLab v3+ with ResNet-50)#13Validation mIoU: 72.8
semi-supervised-semantic-segmentation-on-3CW-BASS (DeepLab v3+ with ResNet-50)#3Validation mIoU: 65.87
semi-supervised-semantic-segmentation-on-4CW-BASS (DeepLab v3+ with ResNet-50)#17Validation mIoU: 75.81%
semi-supervised-semantic-segmentation-on-44CW-BASS (DeepLab v3+ with ResNet-50)#3Validation mIoU: 77.15
semi-supervised-semantic-segmentation-on-9CW-BASS (DeepLab v3+ with ResNet-50)#19Validation mIoU: 76.2

Rank counts only results with a code link.