AINeutralarXiv – CS AI · 3h ago6/10
🧠
Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization
Researchers introduce ANoCo, a training-free method for detecting visual anomalies by measuring how strongly query patches deviate from a normal feature manifold using graph Laplacian energy optimization. The approach achieves strong performance without learnable parameters or message passing, reframing anomaly detection as a non-conformity problem solved through convex optimization.