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/SEER (RegNet10B - linear eval)

SEER (RegNet10B - linear eval)

Reported on 7 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Computer Vision7 results

  • Image ClassificationonDTD
    Accuracy· uses extra data· 2022-02-16
    80.5
    best: 90 (Linear FT(ViT-L/14))
    SOTA
    Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without SupervisionarXiv:2202.08360
  • Image ClassificationonFood-101
    Accuracy (%)· uses extra data· 2022-02-16
    90.3
    best: 92.9 (Bamboo (ViTB/16))
    SOTA
    Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without SupervisionarXiv:2202.08360
  • Image ClassificationonSUN397
    Accuracy· uses extra data· 2022-02-16
    80
    best: 84.8 (µ2Net (ViT-L/16))
    SOTA
    Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without SupervisionarXiv:2202.08360
  • Fine-Grained Image ClassificationonSUN397
    Accuracy· uses extra data· 2022-02-16
    80
    best: 84.8 (µ2Net (ViT-L/16))
    SOTA
    Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without SupervisionarXiv:2202.08360
  • Image ClassificationonEuroSAT
    Accuracy (%)· uses extra data· 2022-02-16
    97.5
    best: 99.41 (DeepEnsembling)
    Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without SupervisionarXiv:2202.08360
  • Image ClassificationonCaltech-101
    Accuracy· uses extra data· 2022-02-16
    91
    best: 97.76 (Pre trained wide-resnet-101)
    Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without SupervisionarXiv:2202.08360
  • Fine-Grained Image ClassificationonCaltech-101
    Accuracy· uses extra data· 2022-02-16
    91
    best: 97.76 (Pre trained wide-resnet-101)
    Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without SupervisionarXiv:2202.08360