GRIT (zero-shot, no VL pretraining, no CBS)
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
- CIDEr· 2022-07-20105.9best: 149.1 (PaLI)
- SPICE· 2022-07-2013.6best: 16.36 (GIT2, Single Model)