AI Paper Atlas

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

Learning Diffusion Models for Multi-View Anomaly Detection

Chieh Liu, Yu-Min Chu, Ting-I Hsieh, Hwann-Tzong Chen, Tyng-Luh Liu

ECCV 2024 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 6 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
train with a view-invariant ControlNet instead of UNet only (ablation)Diffusion-feature anomaly detector · Eyecandies (RGB+3D)Img-ROC: 0.934 -> 0.948Improved
add feature consistency loss across the six views (ablation)view-invariant ControlNet · Eyecandies (RGB+3D)Img-ROC: 0.934 -> 0.948Improved
use decoder block-1 features only rather than blocks 1,2,3 (ablation)diffusion feature memory bank · Eyecandies (RGB+3D)Img-ROC: 0.868 -> 0.948Improved
increase noise intensity in DDIM inversion (ablation)diffusion feature extraction · EyecandiesImg-AUROCImproved
replace UNet with ControlNet for the Nmap-only branch (ablation)Nmap features · Eyecandies (Nmap)Pix-ROC: 0.924 -> 0.828Hurt
fuse RGB and 3D normal score mapsmulti-view anomaly detector · EyecandiesImg-AUROC: 0.888 -> 0.948Improved
apply PatchCore re-weightingscoring · EyecandiesImg-AUROCNo clear effect

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