MAD-Bench is a new benchmark for severity-aligned anomaly detection, and the paper finds MLLM-based scoring ranks severity better than conventional AD models.
Mvtec ad–a comprehensive real-world dataset for unsupervised anomaly detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Are Anomaly Scores Telling the Whole Story? A Benchmark for Multilevel Anomaly Detection
MAD-Bench is a new benchmark for severity-aligned anomaly detection, and the paper finds MLLM-based scoring ranks severity better than conventional AD models.