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/BLIP2 FlanT5-XXL (Fine-tuned)

BLIP2 FlanT5-XXL (Fine-tuned)

Reported on 6 benchmarks across 4 tasks · 1 paper · 4 SOTA

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

Natural Language Processing6 results

  • Visual Question Answering (VQA)onWHOOPS!
    BEM· uses extra data· 2023-03-13
    57
    SOTA
    Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional ImagesarXiv:2303.07274
  • Visual Question Answering (VQA)onWHOOPS!
    Exact Match· uses extra data· 2023-03-13
    21
    SOTA
    Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional ImagesarXiv:2303.07274
  • Image CaptioningonWHOOPS!
    BLEU-4· uses extra data· 2023-03-13
    42
    SOTA
    Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional ImagesarXiv:2303.07274
  • Image CaptioningonWHOOPS!
    CIDEr· uses extra data· 2023-03-13
    177
    SOTA
    Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional ImagesarXiv:2303.07274
  • Explanation GenerationonWHOOPS!
    Human (%)· uses extra data· 2023-03-13
    27
    best: 68 (Ground-truth Caption -> GPT3 (Oracle))
    Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional ImagesarXiv:2303.07274
  • Image-to-Text RetrievalonWHOOPS!
    Specificity· uses extra data· 2023-03-13
    84
    best: 94 (BLIP2 FlanT5-XXL (Text-only FT))
    Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional ImagesarXiv:2303.07274