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/SWEM

SWEM

Reported on 39 benchmarks across 3 tasks · 1 paper

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

Computer Vision39 results

  • VideoonMOSE
    F· 2022-08-22
    54.9
    best: 75.8 (Cutie+ (base, MEGA))
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • VideoonMOSE
    J· 2022-08-22
    46.8
    best: 67.6 (Cutie+ (base, MEGA))
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • VideoonMOSE
    J&F· 2022-08-22
    50.9
    best: 77.9 (SAM2)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • VideoonDAVIS 2017 (val)
    F-measure (Mean)· 2022-08-22
    79.8
    best: 93.4 (Cutie+ (base))
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • VideoonDAVIS 2017 (val)
    J&F· 2022-08-22
    77.2
    best: 90.7 (SAM2)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • VideoonDAVIS 2017 (val)
    Jaccard (Mean)· 2022-08-22
    74.5
    best: 87.5 (Cutie+ (base))
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • VideoonDAVIS (no YouTube-VOS training)
    D16 val (F)· 2022-08-22
    89
    best: 90.6 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • VideoonDAVIS (no YouTube-VOS training)
    D16 val (G)· 2022-08-22
    88.1
    best: 89.4 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • VideoonDAVIS (no YouTube-VOS training)
    D16 val (J)· 2022-08-22
    87.3
    best: 88.2 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • VideoonDAVIS (no YouTube-VOS training)
    D17 val (F)· 2022-08-22
    79.8
    best: 83.1 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • VideoonDAVIS (no YouTube-VOS training)
    D17 val (G)· 2022-08-22
    77.2
    best: 80.4 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • VideoonDAVIS (no YouTube-VOS training)
    D17 val (J)· 2022-08-22
    74.5
    best: 77.7 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • VideoonDAVIS (no YouTube-VOS training)
    FPS· 2022-08-22
    36
    best: 50.1 (TBD)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Video Object SegmentationonMOSE
    F· 2022-08-22
    54.9
    best: 75.8 (Cutie+ (base, MEGA))
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Video Object SegmentationonMOSE
    J· 2022-08-22
    46.8
    best: 67.6 (Cutie+ (base, MEGA))
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Video Object SegmentationonMOSE
    J&F· 2022-08-22
    50.9
    best: 77.9 (SAM2)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Video Object SegmentationonDAVIS 2017 (val)
    F-measure (Mean)· 2022-08-22
    79.8
    best: 93.4 (Cutie+ (base))
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Video Object SegmentationonDAVIS 2017 (val)
    J&F· 2022-08-22
    77.2
    best: 90.7 (SAM2)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Video Object SegmentationonDAVIS 2017 (val)
    Jaccard (Mean)· 2022-08-22
    74.5
    best: 87.5 (Cutie+ (base))
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Video Object SegmentationonDAVIS (no YouTube-VOS training)
    D16 val (F)· 2022-08-22
    89
    best: 90.6 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Video Object SegmentationonDAVIS (no YouTube-VOS training)
    D16 val (G)· 2022-08-22
    88.1
    best: 89.4 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Video Object SegmentationonDAVIS (no YouTube-VOS training)
    D16 val (J)· 2022-08-22
    87.3
    best: 88.2 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Video Object SegmentationonDAVIS (no YouTube-VOS training)
    D17 val (F)· 2022-08-22
    79.8
    best: 83.1 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Video Object SegmentationonDAVIS (no YouTube-VOS training)
    D17 val (G)· 2022-08-22
    77.2
    best: 80.4 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Video Object SegmentationonDAVIS (no YouTube-VOS training)
    D17 val (J)· 2022-08-22
    74.5
    best: 77.7 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Video Object SegmentationonDAVIS (no YouTube-VOS training)
    FPS· 2022-08-22
    36
    best: 50.1 (TBD)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Semi-Supervised Video Object SegmentationonMOSE
    F· 2022-08-22
    54.9
    best: 75.8 (Cutie+ (base, MEGA))
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Semi-Supervised Video Object SegmentationonMOSE
    J· 2022-08-22
    46.8
    best: 67.6 (Cutie+ (base, MEGA))
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Semi-Supervised Video Object SegmentationonMOSE
    J&F· 2022-08-22
    50.9
    best: 77.9 (SAM2)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
    F-measure (Mean)· 2022-08-22
    79.8
    best: 93.4 (Cutie+ (base))
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
    J&F· 2022-08-22
    77.2
    best: 90.7 (SAM2)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
    Jaccard (Mean)· 2022-08-22
    74.5
    best: 87.5 (Cutie+ (base))
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
    D16 val (F)· 2022-08-22
    89
    best: 90.6 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
    D16 val (G)· 2022-08-22
    88.1
    best: 89.4 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
    D16 val (J)· 2022-08-22
    87.3
    best: 88.2 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
    D17 val (F)· 2022-08-22
    79.8
    best: 83.1 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
    D17 val (G)· 2022-08-22
    77.2
    best: 80.4 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
    D17 val (J)· 2022-08-22
    74.5
    best: 77.7 (HMMN)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128
  • Semi-Supervised Video Object SegmentationonDAVIS (no YouTube-VOS training)
    FPS· 2022-08-22
    36
    best: 50.1 (TBD)
    SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-MaximizationarXiv:2208.10128