Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation

Benchmark Model Rank Results
semi-supervised-change-detection-on-levir-cdUniMatch#4IoU: 80.7
semi-supervised-change-detection-on-levir-cd-1UniMatch#4IoU: 82
semi-supervised-change-detection-on-levir-cd-2UniMatch#3IoU: 81.7
semi-supervised-change-detection-on-levir-cd-3UniMatch#3IoU: 82.1
semi-supervised-change-detection-on-whu-10UniMatch#2IoU: 81.7
semi-supervised-change-detection-on-whu-20UniMatch#3IoU: 81.7
semi-supervised-change-detection-on-whu-40UniMatch#3IoU: 85.1
semi-supervised-change-detection-on-whu-5UniMatch#2IoU: 80.2
semi-supervised-medical-image-segmentation-on-2UniMatch#2Dice (Average): 90.47
semi-supervised-medical-image-segmentation-on-3UniMatch#2Dice (Average): 89.92
semi-supervised-medical-image-segmentation-on-4UniMatch#3Dice (Average): 87.61
semi-supervised-semantic-segmentation-on-1UniMatch (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference)#8Validation mIoU: 79.22%
semi-supervised-semantic-segmentation-on-10UniMatch (DeepLab v3 with ResNet-101)#10Validation mIoU: 81.2
semi-supervised-semantic-segmentation-on-2UniMatch (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference)#7Validation mIoU: 77.92%
semi-supervised-semantic-segmentation-on-21UniMatch (DeepLab v3+ with ResNet-101)#6Validation mIoU: 80.94
semi-supervised-semantic-segmentation-on-22UniMatch (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)#8Validation mIoU: 76.59
semi-supervised-semantic-segmentation-on-27UniMatch (DeepLab v3+ with ResNet-101)#10Validation mIoU: 75.20
semi-supervised-semantic-segmentation-on-28UniMatch (DeepLab v3+ with ResNet-101)#10Validation mIoU: 77.20
semi-supervised-semantic-segmentation-on-29UniMatch (DeepLab v3+ with ResNet-101)#10Validation mIoU: 78.80
semi-supervised-semantic-segmentation-on-3UniMatch (DeepLab v3+ with ResNet-101)#2Validation mIoU: 73.0
semi-supervised-semantic-segmentation-on-30UniMatch (DeepLab v3+ with ResNet-101)#10Validation mIoU: 79.90
semi-supervised-semantic-segmentation-on-4UniMatch#4Validation mIoU: 81.92%
semi-supervised-semantic-segmentation-on-41UniMatch#4Validation mIoU: 28.1
semi-supervised-semantic-segmentation-on-42UniMatch#4Validation mIoU: 31.5
semi-supervised-semantic-segmentation-on-8UniMatch#10Validation mIoU: 79.5%
semi-supervised-semantic-segmentation-on-9UniMatch (DeepLab v3+ with ResNet-101)#8Validation mIoU: 80.43
semi-supervised-semantic-segmentation-on-cocoUniMatch#5Validation mIoU: 31.9
semi-supervised-semantic-segmentation-on-coco-1UniMatch#6Validation mIoU: 38.9
semi-supervised-semantic-segmentation-on-coco-2UniMatch#5Validation mIoU: 44.5
semi-supervised-semantic-segmentation-on-coco-3UniMatch#5Validation mIoU: 48.2
semi-supervised-semantic-segmentation-on-coco-4UniMatch#4Validation mIoU: 49.8