AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Robust Zero-shot Anomaly Detection under Limited Auxiliary Anomaly Priors

Guanyu Lu, Fang Zhou, Cheqing Jin

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 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
pretrain on DTD (texture-only anomalies) instead of MVTecbaseline ZSAD models · 12-dataset averageAP: drops of 9.9%-23.3% APHurt
use DIVE instead of baselines under DTD auxiliary dataDIVE · 12-dataset classification avg (DTD-pretrained)AUROC: 81.6 (TPS) -> 87.3Improved
add DIVE under sufficient anomaly diversityDIVE · 12-dataset classification avg (MVTec-pretrained)AUROC: 89.1 (AdaCLIP) -> 90.1Improved
add text embedding injection (shallow + deep) (ablation)DIVE · MVTec classification (DTD-pretrained)AP: 69.5 -> 73.9Improved
add deep-level injection of LLM descriptions (ablation)DIVE · Visa classification (DTD-pretrained)AP: 46.0 -> 50.0Improved
add shallow-level text injection (ablation)DIVE · Visa classification (DTD-pretrained)AP: 49.1 -> 50.0Improved
add disentanglement mechanism (ablation)DIVE · Visa classification (DTD-pretrained)AP: 48.4 -> 50.0Improved
add disentanglement mechanism (ablation)DIVE · MVTec segmentation (DTD-pretrained)AUROC: 89.9 -> 90.5Improved
DIVE vs AA-CLIP on ISIC under RCPRODIVE · ISIC segmentation (DTD-pretrained)RCPRO: 89.3 (AA-CLIP) vs 74.2 (DIVE)Hurt
vary prompting depth P over 3, 6, 9, 12 (ablation)DIVE · MVTec and VisaAUROC/APMixed

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