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/VNE (ResNet-50, SWAD)

VNE (ResNet-50, SWAD)

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 AdaptationonPACS
    Average Accuracy· 2023-04-04
    88.3
    best: 99 (SIMPLE+)
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Domain AdaptationonOffice-Home
    Average Accuracy· 2023-04-04
    71.1
    best: 90.6 (MoA (OpenCLIP, ViT-B/16))
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Domain AdaptationonVLCS
    Average Accuracy· 2023-04-04
    79.7
    best: 85.5 (CAR-FT (CLIP, ViT-B/16))
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Domain AdaptationonTerraIncognita
    Average Accuracy· 2023-04-04
    51.7
    best: 69.6 (UniDG + CORAL + ConvNeXt-B)
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434

Computer Vision4 results

  • Domain GeneralizationonPACS
    Average Accuracy· 2023-04-04
    88.3
    best: 99 (SIMPLE+)
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Domain GeneralizationonOffice-Home
    Average Accuracy· 2023-04-04
    71.1
    best: 90.6 (MoA (OpenCLIP, ViT-B/16))
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Domain GeneralizationonVLCS
    Average Accuracy· 2023-04-04
    79.7
    best: 85.5 (CAR-FT (CLIP, ViT-B/16))
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Domain GeneralizationonTerraIncognita
    Average Accuracy· 2023-04-04
    51.7
    best: 69.6 (UniDG + CORAL + ConvNeXt-B)
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434