Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/DiffusionAD

DiffusionAD

Reported on 9 benchmarks across 2 tasks · 1 paper · 9 SOTA

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

Methodology8 results

Anomaly DetectiononMPDD
Detection AUROC· 2023-03-15
96.2
best: 99.6 (GLASS)
SOTA
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection arXiv:2303.08730
Anomaly DetectiononMPDD
Segmentation AUPRO· 2023-03-15
95.3
best: 98.2 (GLASS)
SOTA
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection arXiv:2303.08730
Anomaly DetectiononMPDD
Segmentation AUROC· 2023-03-15
98.5
best: 99.4 (GLASS)
SOTA
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection arXiv:2303.08730
Anomaly DetectiononVisA
Detection AUROC· 2023-03-15
98.8
best: 99.8 (UniNet)
SOTA
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection arXiv:2303.08730
Anomaly DetectiononVisA
Segmentation AUPRO· 2023-03-15
96
SOTA
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection arXiv:2303.08730
Anomaly DetectiononVisA
Segmentation AUPRO (until 30% FPR)· 2023-03-15
96
best: 96.1 (AnomalyDINO-S (full-shot))
SOTA
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection arXiv:2303.08730
Anomaly DetectiononVisA
Segmentation AUROC· 2023-03-15
98.9
best: 99.1 (Dinomaly ViT-L (model-unified multi-class))
SOTA
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection arXiv:2303.08730
Anomaly DetectiononDAGM2007
Detection AUROC· 2023-03-15
99.6
SOTA
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection arXiv:2303.08730

Graphs1 result

Unsupervised Anomaly DetectiononDAGM2007
Detection AUROC· 2023-03-15
99.6
SOTA
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection arXiv:2303.08730