AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

G2SF: Geometry-Guided Score Fusion for Multimodal Industrial Anomaly Detection

Chengyu Tao, Xuanming Cao, Juan Du

ICCV 2025 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 14 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 consistency loss L_cns to separation loss (ablation)G2SF · MVTec-3D ADI-AUROC: 0.868 -> 0.950Improved
add margin loss L_mar (ablation)G2SF · MVTec-3D ADAUPRO@30%: 0.972 -> 0.975Improved
add margin loss L_mar (ablation)G2SF · MVTec-3D ADI-AUROC: 0.950 -> 0.950No clear effect
add scaling loss L_sc (ablation)G2SF · MVTec-3D ADI-AUROC: 0.950 -> 0.961Improved
add cross-modal alignment loss L_cma (ablation)G2SF · MVTec-3D ADI-AUROC: 0.961 -> 0.971Improved
use min aggregation over adjacent local spaces instead of single space l_i,0 (ablation)G2SF · MVTec-3D ADAUPRO@1%: 0.461 -> 0.468Improved
use min instead of max aggregation (ablation)G2SF · MVTec-3D ADI-AUROC: 0.953 -> 0.971Improved
use min instead of mean aggregation (ablation)G2SF · MVTec-3D ADAUPRO@30%: 0.955 -> 0.979Improved
use min instead of mean aggregation (ablation)G2SF · MVTec-3D ADI-AUROC: 0.972 -> 0.971No clear effect
learn global scaling factors sigma instead of fixed 0.5 (ablation)G2SF · EyecandiesI-AUROC: 0.827 -> 0.902Improved
learn global scaling factors sigma instead of fixed 0.5 (ablation)G2SF · MVTec-3D ADI-AUROC: 0.964 -> 0.971Improved
fuse scaling factors and Euclidean distances (final score s_i) instead of unimodal image score s^R (ablation)G2SF · MVTec-3D ADI-AUROC: 0.849 -> 0.971Improved

Later papers that compared with this method

1 later accepted paper reports G2SF as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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