AI Paper Atlas

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

MATCH: Flow Matching for Multi-View Anomaly Detection

Mathis Kruse, Melissa Schween, Bodo Rosenhahn

ECCV 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 1 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 Hutchinson divergence term (M=1) (ablation)MATCH · Real-IADI-AUROC: 91.172 -> 91.170No clear effect
add Hutchinson divergence term (M=1) (ablation)MATCH · Real-IADFPS: 18.77 -> 5.40Hurt
add Hutchinson divergence term (M=4) (ablation)MATCH · Real-IADFPS: 18.77 -> 1.56Hurt
add divergence term (M=1) (ablation)MATCH · Real-IADmemory (GB): 8.88 -> 10.28Hurt
replace Euler with Midpoint solver (ablation)MATCH · Real-IADI-AUROC: 91.17 -> 91.08No clear effect
replace Euler with RK4 solver (ablation)MATCH · Real-IADI-AUROC: 91.17 -> 91.07No clear effect
replace Euler with adaptive Dopri5 (ablation)MATCH · Real-IADFPS: 13.13 -> 0.48Hurt
increase Euler step size from 0.05 to 0.2 (ablation)MATCH · Real-IADI-AUROC: 91.09 -> 91.17No clear effect
increase Euler step size from 0.05 to 0.2 (ablation)MATCH · Real-IADFPS: 3.26 -> 13.13Improved
use flow matching instead of RealNVP normalizing flowanomaly detector · Real-IADI-AUROC: 90.27 -> 91.17Improved
use flow matching instead of RealNVP normalizing flowanomaly detector · Real-IADbits per dim: 2.10 -> 1.83Improved
use MATCH instead of RD4AD with matched parameter countanomaly detector · Real-IADI-AUROC: 86.75 -> 91.17Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

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