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/VGG-16

VGG-16

Reported on 9 benchmarks across 5 tasks · 3 papers · 1 SOTA

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

Computer Vision5 results

  • Object Recognitiononshape bias
    shape bias· 2018-11-29
    17.2
    best: 98.7 (Imagen)
    ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnessarXiv:1811.12231
  • Image ClassificationonCINIC-10
    Accuracy· 2018-10-02
    87.77
    best: 95.8 (VIT-L/16 (Spinal FC, Background))
    CINIC-10 is not ImageNet or CIFAR-10arXiv:1810.03505
  • Domain GeneralizationonVizWiz-Classification
    Accuracy - All Images· 2014-09-04
    34.7
    best: 57.2 (VOLO-D5)
    Very Deep Convolutional Networks for Large-Scale Image RecognitionarXiv:1409.1556
  • Domain GeneralizationonVizWiz-Classification
    Accuracy - Clean Images· 2014-09-04
    39.5
    best: 450 (ViT-8/B-224)
    Very Deep Convolutional Networks for Large-Scale Image RecognitionarXiv:1409.1556
  • Domain GeneralizationonVizWiz-Classification
    Accuracy - Corrupted Images· 2014-09-04
    28.5
    best: 51.8 (VOLO-D5)
    Very Deep Convolutional Networks for Large-Scale Image RecognitionarXiv:1409.1556

Methodology4 results

  • ClassificationonXImageNet-12
    Robustness Score· 2014-09-04
    0.8845
    best: 0.9062 (DenseNet121)
    SOTA
    Very Deep Convolutional Networks for Large-Scale Image RecognitionarXiv:1409.1556
  • Domain AdaptationonVizWiz-Classification
    Accuracy - All Images· 2014-09-04
    34.7
    best: 57.2 (VOLO-D5)
    Very Deep Convolutional Networks for Large-Scale Image RecognitionarXiv:1409.1556
  • Domain AdaptationonVizWiz-Classification
    Accuracy - Clean Images· 2014-09-04
    39.5
    best: 450 (ViT-8/B-224)
    Very Deep Convolutional Networks for Large-Scale Image RecognitionarXiv:1409.1556
  • Domain AdaptationonVizWiz-Classification
    Accuracy - Corrupted Images· 2014-09-04
    28.5
    best: 51.8 (VOLO-D5)
    Very Deep Convolutional Networks for Large-Scale Image RecognitionarXiv:1409.1556