Hi-gMISnet

Reported on 7 benchmarks across 1 task

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

Medical7 results

Medical Image SegmentationonGlaS
Dice
93.25
Medical Image SegmentationonGlaS
F1
93.25
Medical Image SegmentationonPROMISE12
F1
90.79
Medical Image SegmentationonMoNuSeg
F1
82.5
best: 84.6 (Stardist)
Medical Image SegmentationonCVC-ClinicDB
mIoU
0.9068
best: 0.9343 (DUCK-Net)
Medical Image SegmentationonCVC-ClinicDB
mean Dice
0.9419
best: 0.9684 (DUCK-Net)
Medical Image SegmentationonDRIVE
mIoU
0.6901
best: 0.8406 (FSG-Net)