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/Bamboo (ViT-B/16)

Bamboo (ViT-B/16)

Reported on 8 benchmarks across 2 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 Vision8 results

  • Image ClassificationonDTD
    Accuracy· uses extra data· 2022-03-15
    81.9
    best: 90 (Linear FT(ViT-L/14))
    SOTA
    Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine SynergyarXiv:2203.07845
  • Image ClassificationonCIFAR-10
    Percentage correct· 2022-03-15
    98.2
    best: 99.5 (ViT-H/14)
    Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine SynergyarXiv:2203.07845
  • Image ClassificationonFlowers-102
    Accuracy· uses extra data· 2022-03-15
    99.7
    best: 99.76 (CCT-14/7x2)
    Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine SynergyarXiv:2203.07845
  • Image ClassificationonCIFAR-100
    Percentage correct· uses extra data· 2022-03-15
    90.2
    best: 96.08 (EffNet-L2 (SAM))
    Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine SynergyarXiv:2203.07845
  • Image ClassificationonCaltech-101
    Accuracy· uses extra data· 2022-03-15
    94.8
    best: 97.76 (Pre trained wide-resnet-101)
    Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine SynergyarXiv:2203.07845
  • Image ClassificationonSUN397
    Accuracy· uses extra data· 2022-03-15
    79.5
    best: 84.8 (µ2Net (ViT-L/16))
    Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine SynergyarXiv:2203.07845
  • Fine-Grained Image ClassificationonCaltech-101
    Accuracy· uses extra data· 2022-03-15
    94.8
    best: 97.76 (Pre trained wide-resnet-101)
    Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine SynergyarXiv:2203.07845
  • Fine-Grained Image ClassificationonSUN397
    Accuracy· uses extra data· 2022-03-15
    79.5
    best: 84.8 (µ2Net (ViT-L/16))
    Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine SynergyarXiv:2203.07845