FLAVA (ViT-B, 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.

Natural Language Processing2 results

Image-to-Text RetrievalonCOCO (Common Objects in Context)
Recall@1· 2021-12-08
42.74
best: 85.4 (BLIP-2 (ViT-G, fine-tuned))
FLAVA: A Foundational Language And Vision Alignment Model arXiv:2112.04482
Image-to-Text RetrievalonCOCO (Common Objects in Context)
Recall@5· 2021-12-08
76.76
best: 97 (BLIP-2 (ViT-G, fine-tuned))
FLAVA: A Foundational Language And Vision Alignment Model arXiv:2112.04482