Image-level Anomaly Detection on DTD
99.6AUROCUniADet
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| UniADetLanguage-free=true, Few-shot=2-shot, Backbone=DINOv3 ViT-L/162026.01 | 99.6 | — | 99.7 | |
| UniADetReference Image=Used, Shots=1, Backbone=DINOv3 (ViT-L/16)2026.01 | 99.4 | — | 99.6 | |
| UniADetLanguage-free=true, Few-shot=2-shot, Backbone=DINOv2-R ViT-L/162026.01 | 99.2 | — | 99.6 | |
| UniADetReference Image=Used, Shots=1, Backbone=DINOv2 ViT-L/142026.01 | 98.8 | — | 99.5 | |
| InCtrlLanguage-free=false, Few-shot=2-shot2026.01 | 98.3 | — | 99.1 | |
| AnomalyCLIP+Language-free=false, Few-shot=2-shot2026.01 | 98.2 | — | 99.3 | |
| WinCLIP+Language-free=false, Few-shot=2-shot2026.01 | 98.1 | — | 99.1 | |
| UniADetEvaluation Protocol=Zero-shot, Language-free=true, Backbone=CLIP ViT-L/14@336px2026.01 | 98.1 | — | 99.1 | |
| AnomalyCLIP+Reference Image=Not Used, Shots=02026.01 | 98 | — | 99.2 | |
| AdaptCLIPReference Image=Not Used, Shots=02026.01 | 98 | — | 99.1 | |
| UniADetReference Image=Used, Shots=1, Backbone=CLIP ViT-L/14@336px2026.01 | 98 | — | 99.1 | |
| UniADetLanguage-free=true, Few-shot=2-shot, Backbone=CLIP ViT-L/14@336px2026.01 | 98 | — | 99.1 | |
| WinCLIP+Reference Image=Not Used, Shots=02026.01 | 97.9 | — | 99 | |
| InCtrlReference Image=Not Used, Shots=02026.01 | 97.9 | — | 98.9 | |
| PatchCoreLearning Type=full-shot unsupervised2024.07 | 97.5 | 96.4 | — | |
| AdaptCLIPLanguage-free=false, Few-shot=2-shot2026.01 | 97.4 | — | 99.2 | |
| UniADetEvaluation Protocol=Zero-shot, Language-free=true, Backbone=DINOv3 ViT-L/162026.01 | 97.1 | — | 99 | |
| CDOLearning Type=full-shot unsupervised2024.07 | 96.8 | 95.7 | — | |
| AdaptCLIPEvaluation Protocol=Zero-shot, Language-free=false, Backbone=CLIP ViT-L/14@336px2026.01 | 96 | — | 98.4 | |
| AdaCLIPLearning Type=Zero-Shot (ZSAD)2024.07 | 95.5 | 94.7 | — | |
| WinCLIPEvaluation Protocol=Zero-shot, Language-free=false, Backbone=CLIP ViT-L/14@336px2026.01 | 95.1 | — | 97.7 | |
| Bayes-PFLEvaluation Protocol=Zero-shot, Language-free=false, Backbone=CLIP ViT-L/14@336px2026.01 | 95.1 | — | 98.4 | |
| UniADetEvaluation Protocol=Zero-shot, Language-free=true, Backbone=DINOv2-R ViT-L/162026.01 | 94.3 | — | 98.2 | |
| AnomalyCLIPEvaluation Protocol=Zero-shot, Language-free=false, Backbone=CLIP ViT-L/14@336px2026.01 | 93.9 | — | 97.2 | |
| AdaCLIPEvaluation Protocol=Zero-shot, Language-free=false, Backbone=CLIP ViT-L/14@336px2026.01 | 92.7 | — | 96.4 |