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/DenseNet

DenseNet

Reported on 35 benchmarks across 11 tasks · 1 paper · 12 SOTA

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

Computer Vision17 results

  • Pedestrian Attribute RecognitiononUAV-Human
    Backpack· 2016-08-25
    63.9
    SOTA
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Pedestrian Attribute RecognitiononUAV-Human
    Gender· 2016-08-25
    75
    SOTA
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Pedestrian Attribute RecognitiononUAV-Human
    Hat· 2016-08-25
    67.2
    SOTA
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Pedestrian Attribute RecognitiononUAV-Human
    LCC· 2016-08-25
    54.6
    SOTA
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Pedestrian Attribute RecognitiononUAV-Human
    UCC· 2016-08-25
    49.8
    SOTA
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Pedestrian Attribute RecognitiononUAV-Human
    UCS· 2016-08-25
    73
    SOTA
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Pedestrian Attribute RecognitiononUAV-Human
    LCS· 2016-08-25
    68.9
    best: 69.3 (ResNet)
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Image ClassificationonCIFAR-100
    Percentage correct· uses extra data· 2016-08-25
    82.62
    best: 96.08 (EffNet-L2 (SAM))
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Image ClassificationonSVHN
    Percentage error· 2016-08-25
    1.59
    best: 1 (E2E-M3)
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • HandonRWTH-PHOENIX Handshapes dev set
    Accuracy
    96.05
  • Gesture RecognitiononRWTH-PHOENIX Handshapes dev set
    Accuracy
    96.05
  • Face ReconstructiononMEBeauty
    MAE
    0.674
    best: 0.616 (CNN + Earth Mover Distance)
  • Face ReconstructiononMEBeauty
    Pearson Corr
    0.748
    best: 0.795 (CNN + Earth Mover Distance)
  • Face ReconstructiononMEBeauty
    Root mean square error (RMSE)
    0.877
    best: 0.794 (CNN + Earth Mover Distance)
  • 3D Face ReconstructiononMEBeauty
    MAE
    0.674
    best: 0.616 (CNN + Earth Mover Distance)
  • 3D Face ReconstructiononMEBeauty
    Pearson Corr
    0.748
    best: 0.795 (CNN + Earth Mover Distance)
  • 3D Face ReconstructiononMEBeauty
    Root mean square error (RMSE)
    0.877
    best: 0.794 (CNN + Earth Mover Distance)

Robots7 results

  • Autonomous VehiclesonUAV-Human
    Backpack· 2016-08-25
    63.9
    SOTA
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Autonomous VehiclesonUAV-Human
    Gender· 2016-08-25
    75
    SOTA
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Autonomous VehiclesonUAV-Human
    Hat· 2016-08-25
    67.2
    SOTA
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Autonomous VehiclesonUAV-Human
    LCC· 2016-08-25
    54.6
    SOTA
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Autonomous VehiclesonUAV-Human
    UCC· 2016-08-25
    49.8
    SOTA
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Autonomous VehiclesonUAV-Human
    UCS· 2016-08-25
    73
    SOTA
    Densely Connected Convolutional NetworksarXiv:1608.06993
  • Autonomous VehiclesonUAV-Human
    LCS· 2016-08-25
    68.9
    best: 69.3 (ResNet)
    Densely Connected Convolutional NetworksarXiv:1608.06993

Methodology5 results

  • Multi-Label ClassificationonCheXpert
    AVERAGE AUC ON 14 LABEL
    0.876
    best: 0.933 (CFT (ensemble) Macao Polytechnic University)
  • Multi-Label ClassificationonCheXpert
    NUM RADS BELOW CURVE
    1.2
    best: 3 (inisis)
  • 3DonMEBeauty
    MAE
    0.674
    best: 0.616 (CNN + Earth Mover Distance)
  • 3DonMEBeauty
    Pearson Corr
    0.748
    best: 0.795 (CNN + Earth Mover Distance)
  • 3DonMEBeauty
    Root mean square error (RMSE)
    0.877
    best: 0.794 (CNN + Earth Mover Distance)

Music3 results

  • Facial Recognition and ModellingonMEBeauty
    MAE
    0.674
    best: 0.616 (CNN + Earth Mover Distance)
  • Facial Recognition and ModellingonMEBeauty
    Pearson Corr
    0.748
    best: 0.795 (CNN + Earth Mover Distance)
  • Facial Recognition and ModellingonMEBeauty
    Root mean square error (RMSE)
    0.877
    best: 0.794 (CNN + Earth Mover Distance)

Medical3 results

  • 3D Face ModellingonMEBeauty
    MAE
    0.674
    best: 0.616 (CNN + Earth Mover Distance)
  • 3D Face ModellingonMEBeauty
    Pearson Corr
    0.748
    best: 0.795 (CNN + Earth Mover Distance)
  • 3D Face ModellingonMEBeauty
    Root mean square error (RMSE)
    0.877
    best: 0.794 (CNN + Earth Mover Distance)