APRIL-GAN（zero-shot）

Reported on 4 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.

Methodology4 results

Anomaly DetectiononMVTec AD
Detection AUROC· 2023-05-27
86.1
best: 99.9 (GLASS)
APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD arXiv:2305.17382
Anomaly DetectiononMVTec AD
Segmentation AP· 2023-05-27
40.8
best: 87.6 (WeakREST-Block)
APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD arXiv:2305.17382
Anomaly DetectiononMVTec AD
Segmentation AUPRO· 2023-05-27
44
best: 98.4 (WeakREST-Block)
APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD arXiv:2305.17382
Anomaly DetectiononMVTec AD
Segmentation AUROC· 2023-05-27
87.6
best: 99.7 (WeakREST-Block)
APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD arXiv:2305.17382