Student–Teacher AD (Multiscale)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Methodology2 results

Anomaly DetectiononMVTec AD
Segmentation AP· 2019-11-06
45.5
best: 87.6 (WeakREST-Block)
SOTA
Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings arXiv:1911.02357
Anomaly DetectiononMVTec AD
Segmentation AUPRO· 2019-11-06
91.4
best: 98.4 (WeakREST-Block)
SOTA
Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings arXiv:1911.02357