| Paper | Code | Detection AUROC | ModelName | ReleaseDate |
|---|---|---|---|---|
| VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer | ✓ Link | 96.7 | VisualAD CLIP (zero-shot) | 2026-03-09 |
| From Attraction to Equilibrium: Physics-Inspired Semantic Gravitons for Zero-Shot Anomaly Detection | 96.4 | SGNet | 2026-06-03 | |
| Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detections | ✓ Link | 96.3 | Crane+ (CLIP ViT-L/14@336 + DINOv2-B14, zero-shot) | 2025-04-15 |
| Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection | ✓ Link | 96.2 | Bayes-PFL (ViT-L/14@336, 518px, cross-domain zero-shot) | 2025-03-13 |
| DLVP-CLIP: Enhancing Fine-Grained Zero-Shot Anomaly Detection via Dynamic Local Visual Prompting | 96.2 | DLVP-CLIP | 2026-06-03 | |
| AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors | ✓ Link | 92.9 | AnomalyVFM (RADIOv2.5 ViT-L, synthetic-only zero-shot) | 2026-04-09 |
| AA-CLIP: Enhancing Zero-Shot Anomaly Detection via Anomaly-Aware CLIP | ✓ Link | 80.2 | AA-CLIP | 2025-03-09 |