AI Paper Atlas

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

One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control

Haoxiang Rao, Zhao Wang, Chenyang Si, Yan Lyu, Yuanyi Duan, Fang Zhao, Caifeng Shan

CVPR 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 Dual-Attention Enhancement to TriAG (ablation)O2MAG · MVTec-AD pixel-levelAP: 81.9 -> 83.3Improved
add Anomaly-Guided Optimization to TriAG (ablation)O2MAG · MVTec-AD pixel-levelAP: 81.9 -> 82.7Improved
add both DAE and AGO to TriAG (ablation)O2MAG · MVTec-AD pixel-levelAP: 81.9 -> 86.3Improved
add DAE to TriAG (ablation)O2MAG · MVTec-AD pixel-levelAUROC: 99.0 -> 99.0No clear effect
use O2MAG instead of AnomalyDiffusion for synthetic training dataclassification with ResNet-34 · MVTec-ADAccuracy (%): 70.25 -> 82.35Improved
use O2MAG instead of AnomalyAny (training-free)U-Net detection · MVTec-ADF1-P: 65.1 -> 80.6Improved
use O2MAG instead of baselines for synthetic training dataU-Net detection · MVTec-ADAP-I: 99.7 -> 99.8No clear effect
use O2MAG instead of DualAnoDiff for diversitygeneration · MVTec-ADIC-LPIPS: 0.38 -> 0.30Hurt
use O2MAG instead of baselines for fidelitygeneration · MVTec-ADKID: 62.85 (DFMGAN) -> 45.55Improved
zero-shot cross-class reference (wood-hole to hazelnut-hole) instead of same-class referenceO2MAG · hazelnut-holeAP-P: 90.4 -> 86.8Hurt

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