AI Paper Atlas

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

Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection

Xincheng Yao, Ruoqi Li, Zefeng Qian, lu wang, Chongyang Zhang

ECCV 2024 · Label-efficient and robust learning › OOD and anomaly detection · approach: Anomaly detection with contaminated data · 31 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
replace a single latent Gaussian center with hierarchical Gaussian mixture modeling (ablation)NF-based unified AD (CFLOW-style) · MVTecADimage-level AUROC: 89.0 -> 97.7Improved
use fixed multiple class centers instead of a single center (ablation)NF-based unified AD · MVTecADimage-level AUROC: 89.0 -> 93.1Improved
add learnable inter-class Gaussian mixture modeling over fixed centers (ablation)HGAD · MVTecADimage-level AUROC: 93.1 -> 94.5Improved
add mutual information maximization loss (ablation)HGAD · MVTecADimage-level AUROC: 94.5 -> 96.3 (detection); 96.7 -> 96.6 (localization)Mixed
add intra-class mixed class centers learning (ablation)HGAD (FMC baseline) · MVTecADimage-level AUROC: 93.1 -> 96.3Improved
combine log-likelihood with inter-class entropy as anomaly score (ablation)HGAD · MVTecADimage-level AUROC: 94.4 -> 97.7Improved
increase intra-class centers from 10 to 20 (ablation)HGAD · MVTecADimage-level AUROC: 97.7 -> 97.4No clear effect
increase mutual information loss weight lambda2 from 1 to 100 (ablation)HGAD · MVTecADimage-level AUROC: 96.5 -> 98.4Improved
use two-stage optimization for inter-class then intra-class centers (ablation)HGAD · MVTecADimage-level AUROC: 96.5 -> 97.7Improved
apply HGAD to the NF unified AD model instead of FastFlowFastFlow · MVTecAD (unified)image-level AUROC: 91.8 -> 98.4Improved
HGAD versus UniAD on MVTec3D-RGBUniAD · MVTec3D-RGB (unified)image-level AUROC: 77.5 -> 87.1Improved

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