PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference)

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 VOC 2012 1464 labels
Validation mIoU· 2021-11-25
80.01
best: 90.8 (UniMatch V2 (DINOv2-B))
SOTA
Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation arXiv:2111.12903
Semantic SegmentationonPASCAL VOC 2012 25% labeled
Validation mIoU· 2021-11-25
78.72
best: 81.3 (SemiOVS (w/ PrevMatch, ResNet-101))
SOTA
Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation arXiv:2111.12903

Audio2 results

10-shot image generationonPASCAL VOC 2012 1464 labels
Validation mIoU· 2021-11-25
80.01
best: 90.8 (UniMatch V2 (DINOv2-B))
SOTA
Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation arXiv:2111.12903
10-shot image generationonPASCAL VOC 2012 25% labeled
Validation mIoU· 2021-11-25
78.72
best: 81.3 (SemiOVS (w/ PrevMatch, ResNet-101))
SOTA
Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation arXiv:2111.12903