Fan et al.

Reported on 3 benchmarks across 1 task

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

Computer Vision3 results

Instance SegmentationonCOCO test-dev
AP· uses extra data
13.7
best: 25.9 (WeakSAM-Mask2Former (with SAM))
Instance SegmentationonCOCO test-dev
AP@50· uses extra data
25.5
best: 39.9 (WeakSAM-Mask2Former (with SAM))
Instance SegmentationonCOCO test-dev
AP@75· uses extra data
13.5
best: 27.9 (WeakSAM-Mask2Former (with SAM))