TMUAD detects both structural and logical anomalies by comparing a query image's textual object descriptions, object crops, and image patches against three normal memory banks, reaching state-of-the-art AUROC on seven datasets.
Promptad: Learning prompts with only normal samples for few-shot anomaly detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank
TMUAD detects both structural and logical anomalies by comparing a query image's textual object descriptions, object crops, and image patches against three normal memory banks, reaching state-of-the-art AUROC on seven datasets.