FLAVA (zero-shot)

Reported on 2 benchmarks across 1 task · 1 paper

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

Computer Vision2 results

Image RetrievalonCOCO (Common Objects in Context)
recall@1· 2021-12-08
38.38
best: 68.3 (BLIP-2 ViT-G (fine-tuned))
FLAVA: A Foundational Language And Vision Alignment Model arXiv:2112.04482
Image RetrievalonCOCO (Common Objects in Context)
recall@5· 2021-12-08
67.47
best: 91.8 (VisualSparta)
FLAVA: A Foundational Language And Vision Alignment Model arXiv:2112.04482