CMDS-AD decouples low-frequency normals via diffusion estimator from high-frequency defects in real RGB data using dual streams, a hierarchical mapper, and multiplicative scoring to achieve SOTA 1-shot anomaly detection gains on MVTec 3D-AD and EyeCandies.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection
CMDS-AD decouples low-frequency normals via diffusion estimator from high-frequency defects in real RGB data using dual streams, a hierarchical mapper, and multiplicative scoring to achieve SOTA 1-shot anomaly detection gains on MVTec 3D-AD and EyeCandies.