Validation mIoU: 80.1%
Papers with Code · CC BY-SA 4.0
Semi-Supervised Semantic Segmentation
Models that are trained with a small number of labeled examples and a large number of unlabeled examples and whose aim is to learn to segment an image (i.e. assign a class to every pixel).
논문
Validation mIoU: 40.3%
Validation mIoU: 80.6%
Validation mIoU: 85.1%
Validation mIoU: 78.7%
Validation mIoU: 65.70%
Validation mIoU: 68.69%
Validation mIoU: 66.29%
Validation mIoU: 78.17%
Validation mIoU: 80.4%
Validation mIoU: 81.0
Mean IoU (class): 0.428
Validation mIoU: 79.1%
mIoU (0.1% labels): 40.05mIoU (0.2% labels): 44.62mIoU (1% labels): 49.28
n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation
Validation mIoU: 79.29%
Validation mIoU: 79.22%
Validation mIoU: 79.5%
Validation mIoU: 79.12%
Validation mIoU: 80.28%
Validation mIoU: 79.76%
Validation mIoU: 80.21%
Validation mIoU: 75.33%
Validation mIoU: 35.3
Validation mIoU: 79.11%
Validation mIoU: 80.52