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/Kernel SHAP

Kernel SHAP

Reported on 7 benchmarks across 2 tasks · 1 paper

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

Computer Vision6 results

  • Image AttributiononVGGFace2
    Deletion AUC score (ArcFace ResNet-101)· 2017-05-22
    0.2034
    best: 0.3103 (Grad-CAM)
    A Unified Approach to Interpreting Model PredictionsarXiv:1705.07874
  • Image AttributiononVGGFace2
    Insertion AUC score (ArcFace ResNet-101)· 2017-05-22
    0.6132
    best: 0.6705 (SMDL-Attribution (ICLR version))
    A Unified Approach to Interpreting Model PredictionsarXiv:1705.07874
  • Image AttributiononCUB-200-2011
    Deletion AUC score (ResNet-101)· 2017-05-22
    0.1016
    best: 0.107 (LIME)
    A Unified Approach to Interpreting Model PredictionsarXiv:1705.07874
  • Image AttributiononCUB-200-2011
    Insertion AUC score (ResNet-101)· 2017-05-22
    0.6763
    best: 0.7262 (SMDL-Attribution (ICLR version))
    A Unified Approach to Interpreting Model PredictionsarXiv:1705.07874
  • Image AttributiononCelebA
    Deletion AUC score (ArcFace ResNet-101)· 2017-05-22
    0.1409
    best: 0.2865 (Grad-CAM)
    A Unified Approach to Interpreting Model PredictionsarXiv:1705.07874
  • Image AttributiononCelebA
    Insertion AUC score (ArcFace ResNet-101)· 2017-05-22
    0.5246
    best: 0.5752 (SMDL-Attribution (ICLR version))
    A Unified Approach to Interpreting Model PredictionsarXiv:1705.07874

Miscellaneous1 result

  • Interpretability Techniques for Deep LearningonCelebA
    Insertion AUC score· 2017-05-22
    0.5246
    best: 0.5703 (RISE)
    A Unified Approach to Interpreting Model PredictionsarXiv:1705.07874