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/Deep Unsup.

Deep Unsup.

Reported on 35 benchmarks across 7 tasks

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

Computer Vision25 results

  • Unsupervised Anomaly Detection with Specified Settings -- 20% anomalyonCats and Dogs
    AUC-ROC
    0.773
    best: 0.953 (Shell-Renormalized)
  • Unsupervised Anomaly Detection with Specified Settings -- 20% anomalyoncifar10
    AUC-ROC
    0.702
    best: 0.896 (Shell-Renormalized)
  • Unsupervised Anomaly Detection with Specified Settings -- 20% anomalyonMNIST
    AUC-ROC
    0.779
    best: 0.923 (LVAD)
  • Unsupervised Anomaly Detection with Specified Settings -- 20% anomalyonFashion-MNIST
    AUC-ROC
    0.884
    best: 0.889 (IF)
  • Unsupervised Anomaly Detection with Specified Settings -- 20% anomalyonSTL-10
    AUC-ROC
    0.869
    best: 0.999 (Shell-Renormalized)
  • Unsupervised Anomaly Detection with Specified Settings -- 30% anomalyonASSIRA Cat Vs Dog
    AUC-ROC
    0.74
    best: 0.846 (DAGMM)
  • Unsupervised Anomaly Detection with Specified Settings -- 30% anomalyonSTL-10
    AUC-ROC
    0.866
    best: 0.999 (Shell-Renormalized)
  • Unsupervised Anomaly Detection with Specified Settings -- 30% anomalyonCIFAR-10
    AUC-ROC
    0.689
    best: 0.894 (Shell-Renormalized)
  • Unsupervised Anomaly Detection with Specified Settings -- 30% anomalyonFashion-MNIST
    AUC-ROC
    0.856
    best: 0.889 (IF)
  • Unsupervised Anomaly Detection with Specified Settings -- 30% anomalyonMNIST
    AUC-ROC
    0.835
    best: 0.904 (LVAD)
  • Unsupervised Anomaly Detection with Specified Settings -- 1% anomalyonSTL-10
    AUC-ROC
    0.956
    best: 0.993 (LVAD)
  • Unsupervised Anomaly Detection with Specified Settings -- 1% anomalyonMNIST
    AUC-ROC
    0.891
    best: 0.948 (LVAD)
  • Unsupervised Anomaly Detection with Specified Settings -- 1% anomalyonCIFAR-10
    AUC-ROC
    0.847
    best: 0.94 (LVAD)
  • Unsupervised Anomaly Detection with Specified Settings -- 1% anomalyonCats and Dogs
    AUC-ROC
    0.862
    best: 0.981 (RSRAE)
  • Unsupervised Anomaly Detection with Specified Settings -- 1% anomalyonFashion-MNIST
    AUC-ROC
    0.868
    best: 0.917 (Isolation Forest)
  • Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomalyonMNIST
    AUC-ROC
    0.525
    best: 0.974 (LVAD)
  • Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomalyonSTL-10
    AUC-ROC
    0.384
    best: 0.998 (LVAD)
  • Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomalyonCIFAR-10
    AUC-ROC
    0.841
    best: 0.93 (LVAD)
  • Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomalyonCats and Dogs
    AUC-ROC
    0.545
    best: 0.982 (RSRAE)
  • Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomalyonFashion-MNIST
    AUC-ROC
    0.765
    best: 0.908 (Isolation Forest)
  • Unsupervised Anomaly Detection with Specified Settings -- 10% anomalyonFashion-MNIST
    AUC-ROC
    0.878
    best: 0.915 (IF)
  • Unsupervised Anomaly Detection with Specified Settings -- 10% anomalyonCIFAR-10
    AUC-ROC
    0.847
    best: 0.903 (LVAD)
  • Unsupervised Anomaly Detection with Specified Settings -- 10% anomalyonMNIST
    AUC-ROC
    0.847
    best: 0.938 (LVAD)
  • Unsupervised Anomaly Detection with Specified Settings -- 10% anomalyonSTL-10
    AUC-ROC
    0.906
    best: 0.997 (Shell-Renormalized)
  • Unsupervised Anomaly Detection with Specified Settings -- 10% anomalyonCats and Dogs
    AUC-ROC
    0.862
    best: 0.996 (Shell-Renormalized)

Methodology5 results

  • Anomaly DetectiononASSIRA Cat Vs Dog
    AUC-ROC
    0.74
    best: 0.846 (DAGMM)
  • Anomaly DetectiononSTL-10
    AUC-ROC
    0.866
    best: 0.999 (Shell-Renormalized)
  • Anomaly DetectiononCIFAR-10
    AUC-ROC
    0.689
    best: 0.894 (Shell-Renormalized)
  • Anomaly DetectiononFashion-MNIST
    AUC-ROC
    0.856
    best: 0.889 (IF)
  • Anomaly DetectiononMNIST
    AUC-ROC
    0.835
    best: 0.904 (LVAD)

Graphs5 results

  • Unsupervised Anomaly DetectiononASSIRA Cat Vs Dog
    AUC-ROC
    0.74
    best: 0.846 (DAGMM)
  • Unsupervised Anomaly DetectiononSTL-10
    AUC-ROC
    0.866
    best: 0.999 (Shell-Renormalized)
  • Unsupervised Anomaly DetectiononCIFAR-10
    AUC-ROC
    0.689
    best: 0.894 (Shell-Renormalized)
  • Unsupervised Anomaly DetectiononFashion-MNIST
    AUC-ROC
    0.856
    best: 0.889 (IF)
  • Unsupervised Anomaly DetectiononMNIST
    AUC-ROC
    0.835
    best: 0.904 (LVAD)