PosSAM

Reported on 2 benchmarks across 2 tasks · 1 paper

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

Computer Vision2 results

Open Vocabulary Panoptic SegmentationonADE20K
PQ· 2024-03-14
29.2
best: 31.6 (UMG-CLIP-E/14)
PosSAM: Panoptic Open-vocabulary Segment Anything arXiv:2403.09620
Open Vocabulary Semantic SegmentationonADE20K-847
mIoU· 2024-03-14
14.9
best: 17.3 (UMG-CLIP-E/14)
PosSAM: Panoptic Open-vocabulary Segment Anything arXiv:2403.09620