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/Pyramid Adversarial Training Improves ViT (Im21k)

Pyramid Adversarial Training Improves ViT (Im21k)

Reported on 8 benchmarks across 2 tasks · 1 paper

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

Methodology4 results

  • Domain AdaptationonImageNet-R
    Top-1 Error Rate· uses extra data· 2021-11-30
    42.16
    best: 3.9 (Model soups (BASIC-L))
    Pyramid Adversarial Training Improves ViT PerformancearXiv:2111.15121
  • Domain AdaptationonImageNet-A
    Top-1 accuracy %· uses extra data· 2021-11-30
    62.44
    best: 94.17 (Model soups (BASIC-L))
    Pyramid Adversarial Training Improves ViT PerformancearXiv:2111.15121
  • Domain AdaptationonImageNet-C
    mean Corruption Error (mCE)· uses extra data· 2021-11-30
    36.8
    best: 22 (EfficientNet-L2+RPL)
    Pyramid Adversarial Training Improves ViT PerformancearXiv:2111.15121
  • Domain AdaptationonImageNet-Sketch
    Top-1 accuracy· uses extra data· 2021-11-30
    46.03
    best: 77.18 (Model soups (BASIC-L))
    Pyramid Adversarial Training Improves ViT PerformancearXiv:2111.15121

Computer Vision4 results

  • Domain GeneralizationonImageNet-R
    Top-1 Error Rate· uses extra data· 2021-11-30
    42.16
    best: 3.9 (Model soups (BASIC-L))
    Pyramid Adversarial Training Improves ViT PerformancearXiv:2111.15121
  • Domain GeneralizationonImageNet-A
    Top-1 accuracy %· uses extra data· 2021-11-30
    62.44
    best: 94.17 (Model soups (BASIC-L))
    Pyramid Adversarial Training Improves ViT PerformancearXiv:2111.15121
  • Domain GeneralizationonImageNet-C
    mean Corruption Error (mCE)· uses extra data· 2021-11-30
    36.8
    best: 28.2 (DINOv2 (ViT-g/14, frozen model, linear eval))
    Pyramid Adversarial Training Improves ViT PerformancearXiv:2111.15121
  • Domain GeneralizationonImageNet-Sketch
    Top-1 accuracy· uses extra data· 2021-11-30
    46.03
    best: 77.18 (Model soups (BASIC-L))
    Pyramid Adversarial Training Improves ViT PerformancearXiv:2111.15121