AI Paper Atlas

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

Defect-aware Hybrid Prompt Optimization for Zero-Shot Multi-type Anomaly Detection and Segmentation

Nadeem Nazer, Hongkuan Zhou, Lavdim Halilaj, Ylli Sadikaj, Steffen Staab

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 3 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 shared learnable context tokens to the defect-name anchor prompt (ablation)DAPO · MPDD image-levelAUROC: 53.8 -> 81.2Improved
add the defect-name anchor to soft-only learnable prompts (ablation)DAPO · MPDD image-levelAUROC: 73.7 -> 81.2Improved
share learnable tokens across defect types instead of per-defect tokens (ablation)DAPO · MPDD image-levelAUROC: 70.9 -> 81.2Improved
add progressive injection of learnable tokens (ablation)DAPO · MPDD image-levelAUROC: 79.7 -> 81.2Improved
replace linear adapters with 2-layer adapters (ablation)DAPO · MPDD image-levelAUROC: 81.2 -> 80.5No clear effect
DAPO prompt learning versus handcrafted MultiADS promptsDAPO · MPDD multi-type segmentationpixel F1: 42.8 -> 50.0Improved
DAPO versus MultiADSDAPO · MAD-Real multi-type segmentationpixel F1: 52.5 -> 58.5Improved
DAPO versus MultiADSDAPO · VisA multi-type segmentationpixel AUROC: 93.6 -> 88.9Hurt
DAPO versus MultiADSDAPO · Real-IAD binary detectionimage AUROC: 78.7 -> 84.3Improved
DAPO versus MultiADSDAPO · Internal ASIC binary detectionimage AP: 61.7 -> 79.1Improved
DAPO versus MultiADSDAPO · VisA binary segmentationAUPRO: 89.7 -> 84Hurt
DAPO versus MultiADS on unseen stains defectDAPO · MAD-Real per-defect segmentationpixel F1: 6.1 -> 40.4Improved

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