Model Selection of Zero-shot Anomaly Detectors in the Absence of Labeled Validation Data

Anomaly detection requires detecting abnormal samples in large unlabeled datasets. While progress in deep learning and the advent of foundation models has produced powerful zero-shot anomaly detection methods, their deployment in practice is often hindered by the lack of labeled data -- without it, their detection performance cannot be evaluated reliably. In this work, we propose SWSA (Selection With Synthetic Anomalies): a general-purpose framework to select image-based anomaly detectors with a generated synthetic validation set. Our proposed anomaly generation method …

anomaly anomaly detection cs.cv cs.lg data datasets deep learning deployment detection detection methods foundation model selection performance practice progress samples validation zero-shot