MuSc-V2 introduces a mutual scoring framework that exploits similarity among normal patches in 2D and 3D modalities to detect isolated anomalies without labeled samples.
Shape- consistent one-shot unsupervised domain adaptation for rail surface defect segmentation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samples
MuSc-V2 introduces a mutual scoring framework that exploits similarity among normal patches in 2D and 3D modalities to detect isolated anomalies without labeled samples.