ACR-DSVDD (zero-shot, anomaly ratio=1%)

Reported on 2 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.

Methodology1 result

Anomaly DetectiononAnoShift
ROC-AUC FAR· 2023-02-15
62
best: 62.5 (ACR-NTL (zero-shot, test anomaly ratio=1%))
Zero-Shot Anomaly Detection via Batch Normalization arXiv:2302.07849

Graphs1 result

Unsupervised Anomaly DetectiononAnoShift
ROC-AUC FAR· 2023-02-15
62
best: 62.5 (ACR-NTL (zero-shot, test anomaly ratio=1%))
Zero-Shot Anomaly Detection via Batch Normalization arXiv:2302.07849