U-Net (MaxViT-S)

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 SegmentationonLoveDA
Category mIoU
56.16
Semantic SegmentationonUAVid
Mean IoU
71.88
best: 73.34 (U-Net Ensemble)

Audio2 results

10-shot image generationonLoveDA
Category mIoU
56.16
10-shot image generationonUAVid
Mean IoU
71.88
best: 73.34 (U-Net Ensemble)