BIM-Net

Reported on 6 benchmarks across 2 tasks

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

Medical3 results

Semantic SegmentationonARCH2S
mIoU
18.4
Semantic SegmentationonHePIC 🏛️
mIoU
40.6
best: 43.7 (BIM-Net++)
Semantic SegmentationonS3DIS
mIoU
59.5
best: 76 (Superpoint Transformer)

Audio3 results

10-shot image generationonARCH2S
mIoU
18.4
10-shot image generationonHePIC 🏛️
mIoU
40.6
best: 43.7 (BIM-Net++)
10-shot image generationonS3DIS
mIoU
59.5
best: 76 (Superpoint Transformer)