ICM

Reported on 7 benchmarks across 3 tasks

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

Medical3 results

Semantic SegmentationonNYU Depth v2
Mean IoU
50.7
best: 63.6 (OmniVec2)
Semantic SegmentationonPASCAL Context
mIoU
52.6
best: 71.1 (VPNeXt)
Semantic SegmentationonSUN-RGBD
Mean IoU
50.6
best: 54.6 (GeminiFusion (Swin-Large))

Audio3 results

10-shot image generationonNYU Depth v2
Mean IoU
50.7
best: 63.6 (OmniVec2)
10-shot image generationonPASCAL Context
mIoU
52.6
best: 71.1 (VPNeXt)
10-shot image generationonSUN-RGBD
Mean IoU
50.6
best: 54.6 (GeminiFusion (Swin-Large))

Computer Vision1 result

Scene SegmentationonSUN-RGBD
Mean IoU
50.6