UniMatch (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)

Reported on 2 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.

Medical1 result

Semantic SegmentationonCityscapes 6.25% labeled
Validation mIoU· 2022-08-21
76.59
best: 83.6 (UniMatch V2 (DINOv2-B))
SOTA
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation arXiv:2208.09910

Audio1 result

10-shot image generationonCityscapes 6.25% labeled
Validation mIoU· 2022-08-21
76.59
best: 83.6 (UniMatch V2 (DINOv2-B))
SOTA
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation arXiv:2208.09910