n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation

Benchmark Model Rank Results
semi-supervised-semantic-segmentation-on-1n-CPS (ResNet-50)Validation mIoU: 78.41%
semi-supervised-semantic-segmentation-on-15n-CPS (ResNet-101)Validation mIoU: 80.26%
semi-supervised-semantic-segmentation-on-15n-CPS (ResNet-50)Validation mIoU: 77.07%
semi-supervised-semantic-segmentation-on-2n-CPS (ResNet-50)Validation mIoU: 77.61%
semi-supervised-semantic-segmentation-on-21n-CPS (ResNet-101)Validation mIoU: 75.86
semi-supervised-semantic-segmentation-on-21n-CPS (ResNet-50)Validation mIoU: 72.03
semi-supervised-semantic-segmentation-on-22n-CPS (ResNet-50)Validation mIoU: 76.08
semi-supervised-semantic-segmentation-on-4n-CPSValidation mIoU: 74.21%
semi-supervised-semantic-segmentation-on-4n-CPS (ResNet-101)Validation mIoU: 77.99%
semi-supervised-semantic-segmentation-on-8n-CPS (ResNet-50)Validation mIoU: 79.29%
semi-supervised-semantic-segmentation-on-9n-CPS (ResNet-101)Validation mIoU: 78.97
semi-supervised-semantic-segmentation-on-9n-CPS (ResNet-50)Validation mIoU: 75.85