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/USAD

USAD

Reported on 11 benchmarks across 4 tasks · 1 paper

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

Methodology6 results

  • Anomaly DetectiononSMD
    F1
    93.82
  • Anomaly DetectiononSMD
    Recall
    96.17
  • Anomaly DetectiononSMD
    precision
    93.14
  • Anomaly DetectiononSMAP
    F1
    81.86
    best: 94.1 (DFM (flow matching))
  • Anomaly DetectiononSMAP
    Precision
    76.97
    best: 89.7 (DFM (flow matching))
  • Anomaly DetectiononSMAP
    Recall
    98.31
    best: 99.99 (TranAd)

Graphs3 results

  • Unsupervised Anomaly DetectiononSMAP
    F1
    81.86
    best: 94.1 (DFM (flow matching))
  • Unsupervised Anomaly DetectiononSMAP
    Precision
    76.97
    best: 89.7 (DFM (flow matching))
  • Unsupervised Anomaly DetectiononSMAP
    Recall
    98.31
    best: 99.99 (TranAd)

Time Series2 results

  • Time Series AnalysisonUCR Anomaly Archive
    accuracy· 2023-11-21
    0.276
    best: 0.708 (TimeVQVAE-AD)
    Explainable Time Series Anomaly Detection using Masked Latent Generative ModelingarXiv:2311.12550
  • Time Series Anomaly DetectiononUCR Anomaly Archive
    accuracy· 2023-11-21
    0.276
    best: 0.708 (TimeVQVAE-AD)
    Explainable Time Series Anomaly Detection using Masked Latent Generative ModelingarXiv:2311.12550