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/VPT

VPT

Reported on 16 benchmarks across 6 tasks · 1 paper · 16 SOTA

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

Methodology9 results

  • Generalized Few-Shot ClassificationonCIFAR-100-LT (ρ=50)
    Error Rate· uses extra data· 2022-03-23
    15.2
    best: 9.8 (LIFT (ViT-B/16, ImageNet-21K pre-training))
    SOTA
    Visual Prompt TuningarXiv:2203.12119
  • Generalized Few-Shot ClassificationonCIFAR-100-LT (ρ=10)
    Error Rate· uses extra data· 2022-03-23
    10.4
    best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
    SOTA
    Visual Prompt TuningarXiv:2203.12119
  • Generalized Few-Shot ClassificationonCIFAR-100-LT (ρ=100)
    Error Rate· uses extra data· 2022-03-23
    19
    best: 10.9 (LPT)
    SOTA
    Visual Prompt TuningarXiv:2203.12119
  • Long-tail LearningonCIFAR-100-LT (ρ=50)
    Error Rate· uses extra data· 2022-03-23
    15.2
    best: 9.8 (LIFT (ViT-B/16, ImageNet-21K pre-training))
    SOTA
    Visual Prompt TuningarXiv:2203.12119
  • Long-tail LearningonCIFAR-100-LT (ρ=10)
    Error Rate· uses extra data· 2022-03-23
    10.4
    best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
    SOTA
    Visual Prompt TuningarXiv:2203.12119
  • Long-tail LearningonCIFAR-100-LT (ρ=100)
    Error Rate· uses extra data· 2022-03-23
    19
    best: 10.9 (LPT)
    SOTA
    Visual Prompt TuningarXiv:2203.12119
  • Generalized Few-Shot LearningonCIFAR-100-LT (ρ=50)
    Error Rate· uses extra data· 2022-03-23
    15.2
    best: 9.8 (LIFT (ViT-B/16, ImageNet-21K pre-training))
    SOTA
    Visual Prompt TuningarXiv:2203.12119
  • Generalized Few-Shot LearningonCIFAR-100-LT (ρ=10)
    Error Rate· uses extra data· 2022-03-23
    10.4
    best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
    SOTA
    Visual Prompt TuningarXiv:2203.12119
  • Generalized Few-Shot LearningonCIFAR-100-LT (ρ=100)
    Error Rate· uses extra data· 2022-03-23
    19
    best: 10.9 (LPT)
    SOTA
    Visual Prompt TuningarXiv:2203.12119

Computer Vision6 results

  • Image ClassificationonCIFAR-100-LT (ρ=50)
    Error Rate· uses extra data· 2022-03-23
    15.2
    best: 9.8 (LIFT (ViT-B/16, ImageNet-21K pre-training))
    SOTA
    Visual Prompt TuningarXiv:2203.12119
  • Image ClassificationonCIFAR-100-LT (ρ=10)
    Error Rate· uses extra data· 2022-03-23
    10.4
    best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
    SOTA
    Visual Prompt TuningarXiv:2203.12119
  • Image ClassificationonCIFAR-100-LT (ρ=100)
    Error Rate· uses extra data· 2022-03-23
    19
    best: 10.9 (LPT)
    SOTA
    Visual Prompt TuningarXiv:2203.12119
  • Few-Shot Image ClassificationonCIFAR-100-LT (ρ=50)
    Error Rate· uses extra data· 2022-03-23
    15.2
    best: 9.8 (LIFT (ViT-B/16, ImageNet-21K pre-training))
    SOTA
    Visual Prompt TuningarXiv:2203.12119
  • Few-Shot Image ClassificationonCIFAR-100-LT (ρ=10)
    Error Rate· uses extra data· 2022-03-23
    10.4
    best: 8.7 (LIFT (ViT-B/16, ImageNet-21K pre-training))
    SOTA
    Visual Prompt TuningarXiv:2203.12119
  • Few-Shot Image ClassificationonCIFAR-100-LT (ρ=100)
    Error Rate· uses extra data· 2022-03-23
    19
    best: 10.9 (LPT)
    SOTA
    Visual Prompt TuningarXiv:2203.12119

Natural Language Processing1 result

  • Prompt EngineeringonImageNet-21k
    Accuracy· 2022-03-23
    24.8
    best: 25.3 (POMP)
    SOTA
    Visual Prompt TuningarXiv:2203.12119