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/RVT-Ti*

RVT-Ti*

Reported on 7 benchmarks across 3 tasks · 1 paper · 1 SOTA

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

Computer Vision4 results

  • Domain GeneralizationonImageNet-C
    mean Corruption Error (mCE)· 2021-05-17
    57
    best: 28.2 (DINOv2 (ViT-g/14, frozen model, linear eval))
    SOTA
    Towards Robust Vision TransformerarXiv:2105.07926
  • Image ClassificationonImageNet
    GFLOPs· 2021-05-17
    1.3
    best: 1478 (InternImage-H)
    Towards Robust Vision TransformerarXiv:2105.07926
  • Domain GeneralizationonImageNet-R
    Top-1 Error Rate· 2021-05-17
    56.1
    best: 3.9 (Model soups (BASIC-L))
    Towards Robust Vision TransformerarXiv:2105.07926
  • Domain GeneralizationonImageNet-A
    Top-1 accuracy %· 2021-05-17
    14.4
    best: 94.17 (Model soups (BASIC-L))
    Towards Robust Vision TransformerarXiv:2105.07926

Methodology3 results

  • Domain AdaptationonImageNet-R
    Top-1 Error Rate· 2021-05-17
    56.1
    best: 3.9 (Model soups (BASIC-L))
    Towards Robust Vision TransformerarXiv:2105.07926
  • Domain AdaptationonImageNet-A
    Top-1 accuracy %· 2021-05-17
    14.4
    best: 94.17 (Model soups (BASIC-L))
    Towards Robust Vision TransformerarXiv:2105.07926
  • Domain AdaptationonImageNet-C
    mean Corruption Error (mCE)· 2021-05-17
    57
    best: 22 (EfficientNet-L2+RPL)
    Towards Robust Vision TransformerarXiv:2105.07926