PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection
Open paper
Benchmark
Model
Rank
Results
few-shot-anomaly-detection-on-mvtec-ad-one-shot
PromptAD
#2
Detection AUROC: 94.6
Segmentation AUROC: 95.9
few-shot-anomaly-detection-on-visa-one-shot
PromptAD
#2
Detection AUROC: 86.9
Segmentation AUROC: 96.7
Rank counts only results with a code link.