UNINEXT

Reported on 3 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision3 results

Generalized Referring Expression ComprehensionongRefCOCO
N-acc.· 2023-03-12
50.6
best: 54.7 (SimVG-DB)
SOTA
Universal Instance Perception as Object Discovery and Retrieval arXiv:2303.06674
Generalized Referring Expression ComprehensionongRefCOCO
Precision@(F1=1, IoU≥0.5)· 2023-03-12
58.2
best: 62.1 (SimVG-DB)
SOTA
Universal Instance Perception as Object Discovery and Retrieval arXiv:2303.06674
Zero Shot SegmentationonSegmentation in the Wild
Mean AP· 2023-03-12
42.1
best: 49.6 (Grounded HQ-SAM)
Universal Instance Perception as Object Discovery and Retrieval arXiv:2303.06674