s4GAN+MLMT (DeepLab v2 ImageNet pre-trained)

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

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

Medical2 results

Semantic SegmentationonPASCAL Context 12.5% labeled
Validation mIoU· 2019-08-15
35.3
SOTA
Semi-Supervised Semantic Segmentation with High- and Low-level Consistency arXiv:1908.05724
Semantic SegmentationonPASCAL Context 25% labeled
Validation mIoU· 2019-08-15
37.8
SOTA
Semi-Supervised Semantic Segmentation with High- and Low-level Consistency arXiv:1908.05724

Audio2 results

10-shot image generationonPASCAL Context 12.5% labeled
Validation mIoU· 2019-08-15
35.3
SOTA
Semi-Supervised Semantic Segmentation with High- and Low-level Consistency arXiv:1908.05724
10-shot image generationonPASCAL Context 25% labeled
Validation mIoU· 2019-08-15
37.8
SOTA
Semi-Supervised Semantic Segmentation with High- and Low-level Consistency arXiv:1908.05724