CLIP + FiD
Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing1 result
- Accuracy· 2023-02-23SOTA20.9best: 30.65 (RA-VQAv2 w/ PreFLMR)