UniRef-L (Swin-L)

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.

Computer Vision6 results

Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
F
69.2
best: 76.1 (MPG-SAM 2)
Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
J
65.5
best: 71.7 (MPG-SAM 2)
Instance SegmentationonRefer-YouTube-VOS (2021 public validation)
J&F
67.4
best: 73.9 (MPG-SAM 2)
Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
F
69.2
best: 76.1 (MPG-SAM 2)
Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
J
65.5
best: 71.7 (MPG-SAM 2)
Referring Expression SegmentationonRefer-YouTube-VOS (2021 public validation)
J&F
67.4
best: 73.9 (MPG-SAM 2)