HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Unsupervised Anomaly Detection On Anoshift

Metrics

ROC-AUC FAR
ROC-AUC IID
ROC-AUC NEAR
ROC-AUC-ID (In-Distribution setup)

Results

Performance results of various models on this benchmark

Model Name
ROC-AUC FAR
ROC-AUC IID
ROC-AUC NEAR
ROC-AUC-ID (In-Distribution setup)
Paper TitleRepository
OC-SVM49.5776.8671.4368.73AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
deepSVDD34.5392.6787.0088.24AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
IsoForest27.1686.0975.2681.27AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
ACR-DSVDD (zero-shot, anomaly ratio=1%)62---Zero-Shot Anomaly Detection via Batch Normalization
COPOD50.4285.6254.2480.89AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
ACR-NTL (zero-shot, test anomaly ratio=1%)62.5---Zero-Shot Anomaly Detection via Batch Normalization
SO-GAAL49.3550.4854.5549.90AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
ACR-NTL (zero-shot, test anomaly ratio=20%)62---Zero-Shot Anomaly Detection via Batch Normalization
ECOD Li et al. (2022)49.1984.7644.8779.41AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
LOF34.9691.579.2987.61AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
Internal Contrastive Learning22.4584.8652.2666.99AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
AE for anomalies19.968144.0664.08AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
ACR-DSVDD (zero-shot, anomaly ratio=20%)59.1---Zero-Shot Anomaly Detection via Batch Normalization
BERT28.1584.5486.0579.62AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
LUNAR28.1985.7549.0378.53AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detection
0 of 15 row(s) selected.