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/GPV-2

GPV-2

Reported on 8 benchmarks across 3 tasks · 1 paper · 7 SOTA

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

Natural Language Processing4 results

  • Visual Question Answering (VQA)onGRIT
    VQA (ablation)· 2022-02-04
    63.5
    best: 74.5 (Unified-IOXL)
    SOTA
    Webly Supervised Concept Expansion for General Purpose Vision ModelsarXiv:2202.02317
  • Visual Question Answering (VQA)onGRIT
    VQA (test)· 2022-02-04
    63.2
    best: 74.5 (Unified-IOXL)
    SOTA
    Webly Supervised Concept Expansion for General Purpose Vision ModelsarXiv:2202.02317
  • Visual Question Answering (VQA)onA-OKVQA
    MC Accuracy· 2022-02-04
    53.7
    best: 83.75 (SMoLA-PaLI-X Specialist Model)
    SOTA
    Webly Supervised Concept Expansion for General Purpose Vision ModelsarXiv:2202.02317
  • Visual Question Answering (VQA)onA-OKVQA
    DA VQA Score· 2022-02-04
    40.7
    best: 70.55 (SMoLA-PaLI-X Specialist Model)
    Webly Supervised Concept Expansion for General Purpose Vision ModelsarXiv:2202.02317

Computer Vision4 results

  • Object LocalizationonGRIT
    Localization (ablation)· 2022-02-04
    53.6
    best: 67 (Unified-IOXL)
    SOTA
    Webly Supervised Concept Expansion for General Purpose Vision ModelsarXiv:2202.02317
  • Object LocalizationonGRIT
    Localization (test)· 2022-02-04
    53.6
    best: 67.1 (Unified-IOXL)
    SOTA
    Webly Supervised Concept Expansion for General Purpose Vision ModelsarXiv:2202.02317
  • Object CategorizationonGRIT
    Categorization (ablation)· 2022-02-04
    54.7
    best: 61.7 (Unified-IOXL)
    SOTA
    Webly Supervised Concept Expansion for General Purpose Vision ModelsarXiv:2202.02317
  • Object CategorizationonGRIT
    Categorization (test)· 2022-02-04
    55.1
    best: 60.8 (Unified-IOXL)
    SOTA
    Webly Supervised Concept Expansion for General Purpose Vision ModelsarXiv:2202.02317