AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization

Jungwook Seo, Minjeong Kim, Younkwan Lee, Seungho Shin, Sungyong Baik

CVPR 2026 · Graph learning › Graph self-supervised learning · approach: Graph anomaly detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add bipartite query-reference graph instead of non-bipartite graph (ablation)k-NN + graph energy · MVTec-AD (1-shot)image AUROC: 93.7 -> 95.8Improved
add bipartite query-reference graph instead of non-bipartite graph (ablation)k-NN + graph energy · VisA (1-shot)image AUROC: 86.3 -> 90.5Improved
add anchor-driven retrieval instead of plain k-NN retrieval (ablation)ANoCo · MVTec-AD (1-shot)image AUROC: 95.8 -> 97.9Improved
add anchor-driven retrieval instead of plain k-NN retrieval (ablation)ANoCo · VisA (1-shot)image AUROC: 90.5 -> 92.7Improved
add graph energy on a non-bipartite graph to k-NN (Mahalanobis) (ablation)k-NN · VisA (1-shot)image AUROC: 77.0 -> 86.3Improved
replace energy minimization with message passing (1 round) (ablation)ANoCo · MVTec-AD (1-shot)image AUROC: 87.7 vs 97.9Improved
use more message-passing rounds (1 to 2) (ablation)message passing · MVTec-AD (1-shot)image AUROC: 87.7 -> 82.7Hurt
use product of Euclidean energy and cosine dissimilarity as score instead of L2 only (ablation)ANoCo · MVTec-AD (1-shot)image AUROC: 97.6 -> 97.9No clear effect
use product score instead of cosine distance only (ablation)ANoCo · VisA (1-shot)image AUROC: 92.4 -> 92.7No clear effect
sweep query stabilization coefficient Lambda_q from 1e-24 to 100 (ablation)ANoCo · MVTec-AD and VisA (1-shot)AUROCNo clear effect
increase reference shots from 1 to 4ANoCo · Real-IADimage AUROC: 65.4 -> 83.8Improved
use full-shot references instead of 1-shotANoCo · VisAimage AUROC: 92.7 -> 98.7Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy