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/Dinomaly ViT-L (model-unified multi-class)

Dinomaly ViT-L (model-unified multi-class)

Reported on 9 benchmarks across 1 task · 1 paper · 1 SOTA

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

Methodology9 results

Anomaly DetectiononVisA
F1-Score· 2024-05-23
96.1
best: 98.3 (GLAD)
SOTA
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection arXiv:2405.14325
Anomaly DetectiononMVTec AD
Detection AUROC· uses extra data· 2024-05-23
99.77
best: 99.9 (GLASS)
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection arXiv:2405.14325
Anomaly DetectiononMVTec AD
Segmentation AP· uses extra data· 2024-05-23
70.53
best: 87.6 (WeakREST-Block)
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection arXiv:2405.14325
Anomaly DetectiononMVTec AD
Segmentation AUPRO· uses extra data· 2024-05-23
95.09
best: 98.4 (WeakREST-Block)
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection arXiv:2405.14325
Anomaly DetectiononMVTec AD
Segmentation AUROC· uses extra data· 2024-05-23
98.54
best: 99.7 (WeakREST-Block)
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection arXiv:2405.14325
Anomaly DetectiononVisA
Detection AUROC· 2024-05-23
98.9
best: 99.8 (UniNet)
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection arXiv:2405.14325
Anomaly DetectiononVisA
Segmentation AUPRO· 2024-05-23
94.8
best: 96 (DiffusionAD)
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection arXiv:2405.14325
Anomaly DetectiononVisA
Segmentation AUPRO (until 30% FPR)· 2024-05-23
94.8
best: 96.1 (AnomalyDINO-S (full-shot))
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection arXiv:2405.14325
Anomaly DetectiononVisA
Segmentation AUROC· 2024-05-23
99.1
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection arXiv:2405.14325