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/AGS

AGS

Reported on 32 benchmarks across 2 tasks

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

Computer Vision32 results

  • VideoonDAVIS 2017 (test-dev)
    F-measure (Decay)
    2.6
    best: 37.2 (RGMP)
  • VideoonDAVIS 2017 (test-dev)
    F-measure (Mean)
    49
    best: 91.4 (Cutie+ (base, MEGA))
  • VideoonDAVIS 2017 (test-dev)
    F-measure (Recall)
    51.5
    best: 89.7 (STCN)
  • VideoonDAVIS 2017 (test-dev)
    J&F
    45.6
    best: 88.1 (Cutie+ (base, MEGA))
  • VideoonDAVIS 2017 (test-dev)
    Jaccard (Decay)
    2.6
    best: 35.7 (RVOS)
  • VideoonDAVIS 2017 (test-dev)
    Jaccard (Mean)
    42.1
    best: 84.7 (Cutie+ (base, MEGA))
  • VideoonDAVIS 2017 (test-dev)
    Jaccard (Recall)
    48.5
    best: 85.5 (STCN)
  • VideoonDAVIS 2016 val
    F
    77.4
    best: 90.2 (DEVA (DIS))
  • VideoonDAVIS 2016 val
    G
    78.6
    best: 88.9 (GSANet)
  • VideoonDAVIS 2016 val
    J
    79.7
    best: 88.3 (GSANet)
  • VideoonYouTube-Objects
    J
    69.7
    best: 75.1 (FakeFlow)
  • VideoonDAVIS 2017 (val)
    F-measure (Mean)· uses extra data
    59.5
    best: 93.4 (Cutie+ (base))
  • VideoonDAVIS 2017 (val)
    F-measure (Recall)· uses extra data
    62.8
    best: 94.6 (STCN)
  • VideoonDAVIS 2017 (val)
    J&F· uses extra data
    57.5
    best: 90.7 (SAM2)
  • VideoonDAVIS 2017 (val)
    Jaccard (Mean)· uses extra data
    55.5
    best: 87.5 (Cutie+ (base))
  • VideoonDAVIS 2017 (val)
    Jaccard (Recall)· uses extra data
    61.6
    best: 91.4 (ISVOS (MS))
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    F-measure (Decay)
    2.6
    best: 37.2 (RGMP)
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    F-measure (Mean)
    49
    best: 91.4 (Cutie+ (base, MEGA))
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    F-measure (Recall)
    51.5
    best: 89.7 (STCN)
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    J&F
    45.6
    best: 88.1 (Cutie+ (base, MEGA))
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    Jaccard (Decay)
    2.6
    best: 35.7 (RVOS)
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    Jaccard (Mean)
    42.1
    best: 84.7 (Cutie+ (base, MEGA))
  • Video Object SegmentationonDAVIS 2017 (test-dev)
    Jaccard (Recall)
    48.5
    best: 85.5 (STCN)
  • Video Object SegmentationonDAVIS 2016 val
    F
    77.4
    best: 90.2 (DEVA (DIS))
  • Video Object SegmentationonDAVIS 2016 val
    G
    78.6
    best: 88.9 (GSANet)
  • Video Object SegmentationonDAVIS 2016 val
    J
    79.7
    best: 88.3 (GSANet)
  • Video Object SegmentationonYouTube-Objects
    J
    69.7
    best: 75.1 (FakeFlow)
  • Video Object SegmentationonDAVIS 2017 (val)
    F-measure (Mean)· uses extra data
    59.5
    best: 93.4 (Cutie+ (base))
  • Video Object SegmentationonDAVIS 2017 (val)
    F-measure (Recall)· uses extra data
    62.8
    best: 94.6 (STCN)
  • Video Object SegmentationonDAVIS 2017 (val)
    J&F· uses extra data
    57.5
    best: 90.7 (SAM2)
  • Video Object SegmentationonDAVIS 2017 (val)
    Jaccard (Mean)· uses extra data
    55.5
    best: 87.5 (Cutie+ (base))
  • Video Object SegmentationonDAVIS 2017 (val)
    Jaccard (Recall)· uses extra data
    61.6
    best: 91.4 (ISVOS (MS))