TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

Models/APRIL-GAN

APRIL-GAN

Reported on 6 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Methodology6 results

  • Anomaly DetectiononVisA
    F1-Score· uses extra data· 2023-05-27
    32.3
    best: 98.3 (GLAD)
    SOTA
    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 ADarXiv:2305.17382
  • 2D ClassificationonVisA
    Detection AUROC· uses extra data· 2023-05-27
    78
    SOTA
    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 ADarXiv:2305.17382
  • Anomaly DetectiononVisA
    Detection AUROC· uses extra data· 2023-05-27
    78
    best: 99.8 (UniNet)
    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 ADarXiv:2305.17382
  • Anomaly DetectiononVisA
    Segmentation AUPRO· uses extra data· 2023-05-27
    86.8
    best: 96 (DiffusionAD)
    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 ADarXiv:2305.17382
  • Anomaly DetectiononVisA
    Segmentation AUROC· uses extra data· 2023-05-27
    94.2
    best: 99.1 (Dinomaly ViT-L (model-unified multi-class))
    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 ADarXiv:2305.17382
  • Anomaly DetectiononVisA
    Detection AUROC· uses extra data· 2023-05-27
    78
    best: 99.8 (UniNet)
    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 ADarXiv:2305.17382

Computer Vision1 result

  • Anomaly ClassificationonVisA
    Detection AUROC· uses extra data· 2023-05-27
    78
    SOTA
    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 ADarXiv:2305.17382