SGR (ResNet-101)

Reported on 4 benchmarks across 2 tasks

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

Medical2 results

Semantic SegmentationonADE20K val
mIoU
44.32
best: 62.8 (BEiT-3)
Semantic SegmentationonADE20K
Validation mIoU
44.32
best: 63.6 (ViT-P (InternImage-H))

Audio2 results

10-shot image generationonADE20K val
mIoU
44.32
best: 62.8 (BEiT-3)
10-shot image generationonADE20K
Validation mIoU
44.32
best: 63.6 (ViT-P (InternImage-H))