ClusterCAM

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 SegmentationonCOCO 2014 val
mIoU
41.8
best: 56.8 (DHR (Swin-L, Mask2Former))
Semantic SegmentationonPASCAL VOC 2012 val
Mean IoU
70.3
best: 83.4 (SemPLeS (Swin-L))
Semantic SegmentationonPASCAL VOC 2012 test
Mean IoU
70.7
best: 82.9 (SemPLeS (Swin-L))

Audio3 results

10-shot image generationonCOCO 2014 val
mIoU
41.8
best: 56.8 (DHR (Swin-L, Mask2Former))
10-shot image generationonPASCAL VOC 2012 val
Mean IoU
70.3
best: 83.4 (SemPLeS (Swin-L))
10-shot image generationonPASCAL VOC 2012 test
Mean IoU
70.7
best: 82.9 (SemPLeS (Swin-L))