D3AD

Reported on 5 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology5 results

Anomaly DetectiononBTAD
Detection AUROC· 2024-01-09
95.2
best: 98.3 (CPR)
Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection arXiv:2401.04463
Anomaly DetectiononBTAD
Segmentation AUPRO· 2024-01-09
83.2
best: 97.5 (ReConPatch WRN-50)
Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection arXiv:2401.04463
Anomaly DetectiononVisA
Detection AUROC· 2024-01-09
96
best: 99.8 (UniNet)
Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection arXiv:2401.04463
Anomaly DetectiononVisA
Segmentation AUPRO (until 30% FPR)· 2024-01-09
94.1
best: 96.1 (AnomalyDINO-S (full-shot))
Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection arXiv:2401.04463
Anomaly DetectiononVisA
Segmentation AUROC· 2024-01-09
97.9
best: 99.1 (Dinomaly ViT-L (model-unified multi-class))
Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection arXiv:2401.04463