TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/GRAtt-VIS (Swin-L)

GRAtt-VIS (Swin-L)

Reported on 10 benchmarks across 1 task · 1 paper · 2 SOTA

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

Computer Vision10 results

  • Video Instance SegmentationonYouTube-VIS 2021
    mask AP· uses extra data· 2023-05-26
    60.3
    best: 65.3 (CAVIS(VIT-L, Offline))
    SOTA
    GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance SegmentationarXiv:2305.17096
  • Video Instance SegmentationonOVIS validation
    AR1· uses extra data· 2023-05-26
    19.2
    best: 21.2 (CAVIS(VIT-L, Offline))
    SOTA
    GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance SegmentationarXiv:2305.17096
  • Video Instance SegmentationonYouTube-VIS 2021
    AP50· uses extra data· 2023-05-26
    81.3
    best: 87.3 (CAVIS(VIT-L, Offline))
    GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance SegmentationarXiv:2305.17096
  • Video Instance SegmentationonYouTube-VIS 2021
    AP75· uses extra data· 2023-05-26
    67.1
    best: 73.2 (CAVIS(VIT-L, Offline))
    GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance SegmentationarXiv:2305.17096
  • Video Instance SegmentationonYouTube-VIS 2021
    AR1· uses extra data· 2023-05-26
    48.8
    best: 49.7 (CAVIS(VIT-L, Offline))
    GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance SegmentationarXiv:2305.17096
  • Video Instance SegmentationonYouTube-VIS 2021
    AR10· uses extra data· 2023-05-26
    64.5
    best: 70.7 (DVIS-DAQ(VIT-L, Offline))
    GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance SegmentationarXiv:2305.17096
  • Video Instance SegmentationonOVIS validation
    AP50· uses extra data· 2023-05-26
    69.1
    best: 83.8 (DVIS-DAQ(VIT-L, Offline))
    GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance SegmentationarXiv:2305.17096
  • Video Instance SegmentationonOVIS validation
    AP75· uses extra data· 2023-05-26
    47.8
    best: 63.5 (CAVIS(VIT-L, Offline))
    GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance SegmentationarXiv:2305.17096
  • Video Instance SegmentationonOVIS validation
    AR10· uses extra data· 2023-05-26
    49.4
    best: 61.8 (CAVIS(VIT-L, Offline))
    GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance SegmentationarXiv:2305.17096
  • Video Instance SegmentationonOVIS validation
    mask AP· uses extra data· 2023-05-26
    45.7
    best: 57.1 (DVIS-DAQ(VIT-L, Offline))
    GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance SegmentationarXiv:2305.17096