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/BLIP-2 OPT

BLIP-2 OPT

Reported on 8 benchmarks across 1 task · 1 paper · 8 SOTA

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

Natural Language Processing8 results

  • Visual Question Answering (VQA)onImageNet
    ClipMatch@1· 2024-02-11
    57.1
    SOTA
    Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchyarXiv:2402.07270
  • Visual Question Answering (VQA)onImageNet
    ClipMatch@5· 2024-02-11
    77.24
    SOTA
    Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchyarXiv:2402.07270
  • Visual Question Answering (VQA)onImageNet
    Contains· 2024-02-11
    35.49
    SOTA
    Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchyarXiv:2402.07270
  • Visual Question Answering (VQA)onImageNet
    ExactMatch· 2024-02-11
    0.87
    SOTA
    Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchyarXiv:2402.07270
  • Visual Question Answering (VQA)onImageNet
    Follow-up ClipMatch@1· 2024-02-11
    67.22
    SOTA
    Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchyarXiv:2402.07270
  • Visual Question Answering (VQA)onImageNet
    Follow-up ClipMatch@5· 2024-02-11
    83.54
    SOTA
    Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchyarXiv:2402.07270
  • Visual Question Answering (VQA)onImageNet
    Follow-up Contains· 2024-02-11
    40.31
    SOTA
    Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchyarXiv:2402.07270
  • Visual Question Answering (VQA)onImageNet
    Follow-up ExactMatch· 2024-02-11
    2.54
    SOTA
    Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchyarXiv:2402.07270