UNINEXT (ViT-H, Online)

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

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

Computer Vision3 results

Video Instance SegmentationonOVIS validation
AP50· uses extra data· 2023-03-12
72.5
best: 83.8 (DVIS-DAQ(VIT-L, Offline))
SOTA
Universal Instance Perception as Object Discovery and Retrieval arXiv:2303.06674
Video Instance SegmentationonOVIS validation
AP75· uses extra data· 2023-03-12
52.2
best: 63.5 (CAVIS(VIT-L, Offline))
SOTA
Universal Instance Perception as Object Discovery and Retrieval arXiv:2303.06674
Video Instance SegmentationonOVIS validation
mask AP· uses extra data· 2023-03-12
49
best: 57.1 (DVIS-DAQ(VIT-L, Offline))
SOTA
Universal Instance Perception as Object Discovery and Retrieval arXiv:2303.06674