DVIS++(R50, Online)

Reported on 5 benchmarks across 1 task · 1 paper

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

Computer Vision5 results

Video Instance SegmentationonOVIS validation
AP50· uses extra data· 2023-12-20
62.8
best: 83.8 (DVIS-DAQ(VIT-L, Offline))
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Video Instance SegmentationonOVIS validation
AP75· uses extra data· 2023-12-20
37.3
best: 63.5 (CAVIS(VIT-L, Offline))
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Video Instance SegmentationonOVIS validation
AR1· uses extra data· 2023-12-20
15.8
best: 21.2 (CAVIS(VIT-L, Offline))
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Video Instance SegmentationonOVIS validation
AR10· uses extra data· 2023-12-20
42.9
best: 61.8 (CAVIS(VIT-L, Offline))
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305
Video Instance SegmentationonOVIS validation
mask AP· uses extra data· 2023-12-20
37.2
best: 57.1 (DVIS-DAQ(VIT-L, Offline))
DVIS++: Improved Decoupled Framework for Universal Video Segmentation arXiv:2312.13305