A test-time prototype refinement framework using optimal transport improves few-shot industrial anomaly detection accuracy on MVTec, VisA, MPDD, and RealIAD.
Convex optimization: Algorithms and complexity.Foundations and Trends®in Machine Learning, 8(3-4):231–357, 2015
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
unclear 1representative citing papers
citing papers explorer
-
FastRef:Fast Prototype Refinement for Few-Shot Industrial Anomaly Detection
A test-time prototype refinement framework using optimal transport improves few-shot industrial anomaly detection accuracy on MVTec, VisA, MPDD, and RealIAD.