AI Paper Atlas

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

Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and Detection

Long Qian, Bingke Zhu, Yingying Chen, Ming Tang, Jinqiao Wang

AAAI 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 0 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 DTD/Perlin synthesis with ARAS (ablation)DRAEM · MVTec ADimage/pixel AUROC: 98.0/97.2 -> 98.6/97.9Improved
replace SDAS diffusion synthesis with ARAS (ablation)RealNet · MVTec ADpixel AUROC: 99.0 -> 99.3Improved
replace SDAS diffusion synthesis with ARAS (ablation)RealNet · MVTec ADimage AUROC: 99.6 -> 99.6No clear effect
add hinge quality-aware weighting (ablation)RealNet+ARAS · MVTec ADpixel AUROC: 99.3 -> 99.8Improved
add softmax quality-aware weighting (QAW) (ablation)RealNet+ARAS · MVTec ADpixel AUROC: 99.3 -> 99.9Improved
use softmax rather than hinge weighting (ablation)RealNet+ARAS · MVTec ADpixel AUROC: 99.8 -> 99.9Improved
QARAD over RealNetRealNet · VisAimage/pixel AUROC: 97.8/98.8 -> 98.9/99.8Improved
QARAD over RealNetRealNet · MVTec ADimage/pixel AUROC: 99.6/99.0 -> 99.7/99.8Improved
QARAD over RealNetRealNet · BTADimage/pixel AUROC: 96.1/97.9 -> 96.7/98.0Improved
ARAS in place of diffusion-based synthesisRealNet · synthesis time per imageseconds: 7.51 -> 1.49Improved
add QAW (CLIP similarity scoring)QARAD · detector trainingtrain time (s/ep): 100.89 -> 110.36Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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