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/null

null

Reported on 65 benchmarks across 10 tasks · 1 paper · 4 SOTA

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

Robots26 results

  • Vision and Language NavigationonVLN Challenge
    error· 2019-04-08
    3.26
    best: 1.61 (human)
    SOTA
    Learning to Navigate Unseen Environments: Back Translation with Environmental DropoutarXiv:1904.04195
  • Vision and Language NavigationonVLN Challenge
    length· 2019-04-08
    686.82
    best: 1257.38 (Speaker-Follower)
    SOTA
    Learning to Navigate Unseen Environments: Back Translation with Environmental DropoutarXiv:1904.04195
  • Vision and Language NavigationonVLN Challenge
    oracle success· 2019-04-08
    0.99
    best: 1 (FOAM-Beam Search)
    SOTA
    Learning to Navigate Unseen Environments: Back Translation with Environmental DropoutarXiv:1904.04195
  • Vision and Language NavigationonVLN Challenge
    success· 2019-04-08
    0.69
    best: 0.86 (human)
    SOTA
    Learning to Navigate Unseen Environments: Back Translation with Environmental DropoutarXiv:1904.04195
  • Vision and Language NavigationonVLN Challenge
    spl· 2019-04-08
    0.01
    best: 0.76 (human)
    Learning to Navigate Unseen Environments: Back Translation with Environmental DropoutarXiv:1904.04195
  • Vision and Language NavigationonVLN Challenge
    spl· 2019-04-08
    0.01
    best: 0.76 (human)
    Learning to Navigate Unseen Environments: Back Translation with Environmental DropoutarXiv:1904.04195
  • Autonomous VehiclesonArgoverse CVPR 2020
    DAC (K=6)
    0.8857
    best: 0.9931 (lt_cont_k6)
  • Autonomous VehiclesonArgoverse CVPR 2020
    MR (K=1)
    0.8348
    best: 1 (jwlhs104)
  • Autonomous VehiclesonArgoverse CVPR 2020
    MR (K=6)
    0.8348
    best: 0.9893 (WST)
  • Autonomous VehiclesonArgoverse CVPR 2020
    brier-minFDE (K=6)
    7.8875
    best: 26.4057 (WST)
  • Autonomous VehiclesonArgoverse CVPR 2020
    minADE (K=1)
    3.5333
    best: 10634487.5868 (ewta)
  • Autonomous VehiclesonArgoverse CVPR 2020
    minADE (K=6)
    3.5333
    best: 155985.7998 (ewta)
  • Autonomous VehiclesonArgoverse CVPR 2020
    minFDE (K=1)
    7.8875
    best: 57.7046 (jwlhs104)
  • Autonomous VehiclesonArgoverse CVPR 2020
    minFDE (K=6)
    7.8875
    best: 25.7113 (WST)
  • Autonomous DrivingonArgoverse CVPR 2020
    DAC (K=6)
    0.8857
    best: 0.9931 (lt_cont_k6)
  • Autonomous DrivingonArgoverse CVPR 2020
    MR (K=1)
    0.8348
    best: 1 (jwlhs104)
  • Autonomous DrivingonArgoverse CVPR 2020
    MR (K=6)
    0.8348
    best: 0.9893 (WST)
  • Autonomous DrivingonArgoverse CVPR 2020
    brier-minFDE (K=6)
    7.8875
    best: 26.4057 (WST)
  • Autonomous DrivingonArgoverse CVPR 2020
    minADE (K=1)
    3.5333
    best: 10634487.5868 (ewta)
  • Autonomous DrivingonArgoverse CVPR 2020
    minADE (K=6)
    3.5333
    best: 155985.7998 (ewta)
  • Autonomous DrivingonArgoverse CVPR 2020
    minFDE (K=1)
    7.8875
    best: 57.7046 (jwlhs104)
  • Autonomous DrivingonArgoverse CVPR 2020
    minFDE (K=6)
    7.8875
    best: 25.7113 (WST)
  • Vision and Language NavigationonVLN Challenge
    error
    4.57
    best: 1.61 (human)
  • Vision and Language NavigationonVLN Challenge
    length
    1214.94
    best: 1257.38 (Speaker-Follower)
  • Vision and Language NavigationonVLN Challenge
    oracle success
    0.96
    best: 1 (FOAM-Beam Search)
  • Vision and Language NavigationonVLN Challenge
    success
    0.56
    best: 0.86 (human)

Methodology24 results

  • 3DonLVIS v1.0 val
    AP
    25.8
    best: 51.6 (CP-DETR-Pro(without LVIS data))
  • 3DonLVIS v1.0 val
    AP50
    39.76
    best: 63.1 (best_single_model_val)
  • 3DonLVIS v1.0 val
    AP75
    27.53
    best: 51.15 (best_single_model_val)
  • 3DonLVIS v1.0 val
    APc
    25.51
    best: 47.47 (best_single_model_val)
  • 3DonLVIS v1.0 val
    APf
    31.39
    best: 51.44 (best_single_model_val)
  • 3DonLVIS v1.0 val
    APr
    13.82
    best: 38.91 (best_single_model_val)
  • 2D ClassificationonLVIS v1.0 val
    AP
    25.8
    best: 51.6 (CP-DETR-Pro(without LVIS data))
  • 2D ClassificationonLVIS v1.0 val
    AP50
    39.76
    best: 63.1 (best_single_model_val)
  • 2D ClassificationonLVIS v1.0 val
    AP75
    27.53
    best: 51.15 (best_single_model_val)
  • 2D ClassificationonLVIS v1.0 val
    APc
    25.51
    best: 47.47 (best_single_model_val)
  • 2D ClassificationonLVIS v1.0 val
    APf
    31.39
    best: 51.44 (best_single_model_val)
  • 2D ClassificationonLVIS v1.0 val
    APr
    13.82
    best: 38.91 (best_single_model_val)
  • 2D Object DetectiononLVIS v1.0 val
    AP
    25.8
    best: 51.6 (CP-DETR-Pro(without LVIS data))
  • 2D Object DetectiononLVIS v1.0 val
    AP50
    39.76
    best: 63.1 (best_single_model_val)
  • 2D Object DetectiononLVIS v1.0 val
    AP75
    27.53
    best: 51.15 (best_single_model_val)
  • 2D Object DetectiononLVIS v1.0 val
    APc
    25.51
    best: 47.47 (best_single_model_val)
  • 2D Object DetectiononLVIS v1.0 val
    APf
    31.39
    best: 51.44 (best_single_model_val)
  • 2D Object DetectiononLVIS v1.0 val
    APr
    13.82
    best: 38.91 (best_single_model_val)
  • 16konLVIS v1.0 val
    AP
    25.8
    best: 51.6 (CP-DETR-Pro(without LVIS data))
  • 16konLVIS v1.0 val
    AP50
    39.76
    best: 63.1 (best_single_model_val)
  • 16konLVIS v1.0 val
    AP75
    27.53
    best: 51.15 (best_single_model_val)
  • 16konLVIS v1.0 val
    APc
    25.51
    best: 47.47 (best_single_model_val)
  • 16konLVIS v1.0 val
    APf
    31.39
    best: 51.44 (best_single_model_val)
  • 16konLVIS v1.0 val
    APr
    13.82
    best: 38.91 (best_single_model_val)

Computer Vision20 results

  • Object DetectiononLVIS v1.0 val
    AP
    25.8
    best: 51.6 (CP-DETR-Pro(without LVIS data))
  • Object DetectiononLVIS v1.0 val
    AP50
    39.76
    best: 63.1 (best_single_model_val)
  • Object DetectiononLVIS v1.0 val
    AP75
    27.53
    best: 51.15 (best_single_model_val)
  • Object DetectiononLVIS v1.0 val
    APc
    25.51
    best: 47.47 (best_single_model_val)
  • Object DetectiononLVIS v1.0 val
    APf
    31.39
    best: 51.44 (best_single_model_val)
  • Object DetectiononLVIS v1.0 val
    APr
    13.82
    best: 38.91 (best_single_model_val)
  • Motion ForecastingonArgoverse CVPR 2020
    DAC (K=6)
    0.8857
    best: 0.9931 (lt_cont_k6)
  • Motion ForecastingonArgoverse CVPR 2020
    MR (K=1)
    0.8348
    best: 1 (jwlhs104)
  • Motion ForecastingonArgoverse CVPR 2020
    MR (K=6)
    0.8348
    best: 0.9893 (WST)
  • Motion ForecastingonArgoverse CVPR 2020
    brier-minFDE (K=6)
    7.8875
    best: 26.4057 (WST)
  • Motion ForecastingonArgoverse CVPR 2020
    minADE (K=1)
    3.5333
    best: 10634487.5868 (ewta)
  • Motion ForecastingonArgoverse CVPR 2020
    minADE (K=6)
    3.5333
    best: 155985.7998 (ewta)
  • Motion ForecastingonArgoverse CVPR 2020
    minFDE (K=1)
    7.8875
    best: 57.7046 (jwlhs104)
  • Motion ForecastingonArgoverse CVPR 2020
    minFDE (K=6)
    7.8875
    best: 25.7113 (WST)
  • Few-Shot Object DetectiononLVIS v1.0 val
    AP
    25.8
    best: 47.55 (best_single_model_val)
  • Few-Shot Object DetectiononLVIS v1.0 val
    AP50
    39.76
    best: 63.1 (best_single_model_val)
  • Few-Shot Object DetectiononLVIS v1.0 val
    AP75
    27.53
    best: 51.15 (best_single_model_val)
  • Few-Shot Object DetectiononLVIS v1.0 val
    APc
    25.51
    best: 47.47 (best_single_model_val)
  • Few-Shot Object DetectiononLVIS v1.0 val
    APf
    31.39
    best: 51.44 (best_single_model_val)
  • Few-Shot Object DetectiononLVIS v1.0 val
    APr
    13.82
    best: 38.91 (best_single_model_val)