n-CPS (ResNet-101)

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Semantic SegmentationonPASCAL VOC 2012 25% labeled
Validation mIoU· 2021-12-14
78.97
best: 81.3 (SemiOVS (w/ PrevMatch, ResNet-101))
SOTA
n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation arXiv:2112.07528
Semantic SegmentationonPascal VOC 2012 6.25% labeled
Validation mIoU· 2021-12-14
75.86
best: 82 (SemiOVS (w/ PrevMatch, ResNet-101))
n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation arXiv:2112.07528

Audio2 results

10-shot image generationonPASCAL VOC 2012 25% labeled
Validation mIoU· 2021-12-14
78.97
best: 81.3 (SemiOVS (w/ PrevMatch, ResNet-101))
SOTA
n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation arXiv:2112.07528
10-shot image generationonPascal VOC 2012 6.25% labeled
Validation mIoU· 2021-12-14
75.86
best: 82 (SemiOVS (w/ PrevMatch, ResNet-101))
n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation arXiv:2112.07528