Industrial Inspection

Anomaly Detection

Detecting defects and anomalies in manufacturing (MVTec AD, VisA).

7
Datasets
17
Results
auroc
Canonical metric
Canonical Benchmark

MVTec AD

5,354 high-resolution images across 15 object and texture categories. The gold standard for industrial anomaly detection with pixel-level annotations.

Primary metric: auroc
View full leaderboard

Top 10

Leading models on MVTec AD.

RankModelImage AUROCYearSource
1
SimpleNet
99.62026paper
2
simplenet
99.62025paper
3
fastflow
99.42025paper
4
patchcore
99.12025paper
5
efficientad
99.12025paper
6
PatchCore
99.12026paper
7
EfficientAD
99.12026paper
8
reverse-distillation
98.52025paper
9
cflow-ad
98.32025paper
10
draem
98.02025paper

All datasets

7 datasets tracked for this task.

MVTec AD

CANONICAL
11results·auroc
Top: SimpleNet — 99.6

VisA

3results·auroc
Top: simplenet — 95.5

NEU-DET

1result·map
Top: defectdet-resnet — 78.4

Severstal Steel Defect

1result·dice
Top: yolov8-weld — 91.2

Weld Defect X-Ray

1result·map
Top: yolov8-weld — 87.3

KolektorSDD2

0results·auroc

MVTec 3D-AD

0results·auroc

Related tasks

Other tasks in Industrial Inspection.

Steel Defect DetectionSurface Defect DetectionWeld Inspection