AI Paper Atlas

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

AnoStyler: Text-Driven Localized Anomaly Generation via Lightweight Style Transfer

Yulim So, Seokho Kang

AAAI 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 8 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 modified global directional loss (Lgdir) (ablation)AnoStyler · MVTec-ADI-AUC (%): 88.2 -> 95.2Improved
add modified patch-wise directional loss (Lpdir) (ablation)AnoStyler · MVTec-ADI-AUC (%): 95.2 -> 96.7Improved
add masked CLIP loss (Lmclip) (ablation)AnoStyler · MVTec-ADI-AUC (%): 96.7 -> 98.0Improved
add masked CLIP loss (Lmclip) (ablation)AnoStyler · MVTec-ADIS: 1.96 -> 2.04Improved
use baseline CLIPstyler objective without mask-aware losses (ablation)AnoStyler · MVTec-ADP-AUC (%): 94.4 -> 85.7Hurt
use text-driven style transfer instead of AnomalyAny diffusionAnoStyler · MVTec-ADIC-L: 0.33 -> 0.32No clear effect
use AnoStyler anomalies instead of AnomalyAny for detectionAnoStyler · MVTec-ADP-AUC (%): 89.0 -> 94.4Improved
use AnoStyler anomalies instead of RealNet for detectionAnoStyler · VisAI-AUC (%): 92.6 -> 93.9Improved
use AnoStyler instead of RealNet on VisA pixel APAnoStyler · VisAP-AP (%): 33.3 -> 31.4Hurt
zero-shot AnoStyler vs few-shot AnoDiffAnoStyler · MVTec-ADI-AUC (%): 99.2 -> 98.0Hurt
lightweight U-Net style transfer instead of diffusionAnoStyler · per-image costTFLOPs: 22.8 -> 9.5Improved

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