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/DiscFace

DiscFace

Reported on 36 benchmarks across 7 tasks

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

Computer Vision16 results

  • Face VerificationonAgeDB-30
    Accuracy
    0.9835
    best: 0.987 (PartialFC(R200))
  • Face VerificationonCALFW
    Accuracy
    96.15
  • Face VerificationonQMUL-SurvFace
    TAR @ FAR=0.1
    35.9
  • Face VerificationonCPLFW
    Accuracy
    93.37
  • Face ReconstructiononLFW
    Accuracy· uses extra data
    0.9983
    best: 0.998667 (GhostFaceNetV2-1 (MS1MV3))
  • Face ReconstructiononCFP-FP
    Accuracy
    0.9854
    best: 0.9951 (PartialFC (R200))
  • Face ReconstructiononAgeDB-30
    Accuracy
    0.9835
    best: 71.62 (USynthFace)
  • Face ReconstructiononCALFW
    Accuracy
    96.15
  • Face ReconstructiononQMUL-SurvFace
    TAR @ FAR=0.1
    35.9
  • Face ReconstructiononCPLFW
    Accuracy
    93.37
  • 3D Face ReconstructiononLFW
    Accuracy· uses extra data
    0.9983
    best: 0.998667 (GhostFaceNetV2-1 (MS1MV3))
  • 3D Face ReconstructiononCFP-FP
    Accuracy
    0.9854
    best: 0.9951 (PartialFC (R200))
  • 3D Face ReconstructiononAgeDB-30
    Accuracy
    0.9835
    best: 71.62 (USynthFace)
  • 3D Face ReconstructiononCALFW
    Accuracy
    96.15
  • 3D Face ReconstructiononQMUL-SurvFace
    TAR @ FAR=0.1
    35.9
  • 3D Face ReconstructiononCPLFW
    Accuracy
    93.37

Methodology8 results

  • Face RecognitiononLFW
    Accuracy· uses extra data
    0.9983
    best: 0.998667 (GhostFaceNetV2-1 (MS1MV3))
  • Face RecognitiononCFP-FP
    Accuracy
    0.9854
    best: 0.9933 (GhostFaceNetV2-1)
  • 3DonLFW
    Accuracy· uses extra data
    0.9983
    best: 0.998667 (GhostFaceNetV2-1 (MS1MV3))
  • 3DonCFP-FP
    Accuracy
    0.9854
    best: 0.9951 (PartialFC (R200))
  • 3DonAgeDB-30
    Accuracy
    0.9835
    best: 71.62 (USynthFace)
  • 3DonCALFW
    Accuracy
    96.15
  • 3DonQMUL-SurvFace
    TAR @ FAR=0.1
    35.9
  • 3DonCPLFW
    Accuracy
    93.37

Music6 results

  • Facial Recognition and ModellingonLFW
    Accuracy· uses extra data
    0.9983
    best: 0.998667 (GhostFaceNetV2-1 (MS1MV3))
  • Facial Recognition and ModellingonCFP-FP
    Accuracy
    0.9854
    best: 0.9951 (PartialFC (R200))
  • Facial Recognition and ModellingonAgeDB-30
    Accuracy
    0.9835
    best: 71.62 (USynthFace)
  • Facial Recognition and ModellingonCALFW
    Accuracy
    96.15
  • Facial Recognition and ModellingonQMUL-SurvFace
    TAR @ FAR=0.1
    35.9
  • Facial Recognition and ModellingonCPLFW
    Accuracy
    93.37

Medical6 results

  • 3D Face ModellingonLFW
    Accuracy· uses extra data
    0.9983
    best: 0.998667 (GhostFaceNetV2-1 (MS1MV3))
  • 3D Face ModellingonCFP-FP
    Accuracy
    0.9854
    best: 0.9951 (PartialFC (R200))
  • 3D Face ModellingonAgeDB-30
    Accuracy
    0.9835
    best: 71.62 (USynthFace)
  • 3D Face ModellingonCALFW
    Accuracy
    96.15
  • 3D Face ModellingonQMUL-SurvFace
    TAR @ FAR=0.1
    35.9
  • 3D Face ModellingonCPLFW
    Accuracy
    93.37