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/I-VNE+ (ResNet-50)

I-VNE+ (ResNet-50)

Reported on 10 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Computer Vision10 results

  • Image ClassificationonImageNet - 10% labeled data
    Top 1 Accuracy· 2023-04-04
    69.1
    SOTA
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Image ClassificationonImageNet - 10% labeled data
    Top 5 Accuracy· 2023-04-04
    89.9
    best: 92.6 (SimMatch + EPASS (ResNet-50))
    SOTA
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Image ClassificationonImageNet - 1% labeled data
    Top 1 Accuracy· 2023-04-04
    55.8
    SOTA
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Semi-Supervised Image ClassificationonImageNet - 10% labeled data
    Top 1 Accuracy· 2023-04-04
    69.1
    SOTA
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Semi-Supervised Image ClassificationonImageNet - 10% labeled data
    Top 5 Accuracy· 2023-04-04
    89.9
    best: 92.6 (SimMatch + EPASS (ResNet-50))
    SOTA
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Semi-Supervised Image ClassificationonImageNet - 1% labeled data
    Top 1 Accuracy· 2023-04-04
    55.8
    SOTA
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Image ClassificationonImageNet - 1% labeled data
    Top 5 Accuracy· 2023-04-04
    81
    best: 93.1 (Semi-ViT (ViT-Huge))
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Image ClassificationonImageNet
    Top 1 Accuracy· 2023-04-04
    72.1
    best: 88.3 (Unicom (ViT-L/14@336px) (Finetuned))
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Image ClassificationonImageNet
    Top 5 Accuracy· 2023-04-04
    91
    best: 99.02 (Florence-CoSwin-H)
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434
  • Semi-Supervised Image ClassificationonImageNet - 1% labeled data
    Top 5 Accuracy· 2023-04-04
    81
    best: 93.1 (Semi-ViT (ViT-Huge))
    VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionarXiv:2304.01434