Image-to-Text Retrieval on Flickr30k (Recall)
96.7RecallFineViT/14
Evaluation results
| Method | Links | |
|---|---|---|
| FineViT/14Params=0.86B, Zero-shot=true2026.03 | 96.7 | |
| SigLIP2-g/16Params=1B, Zero-shot=true2026.03 | 95.4 | |
| SigLIP2-so400m/14Params=0.4B, Zero-shot=true2026.03 | 94.9 | |
| SigLIP-so400m/14Params=0.4B, Zero-shot=true2026.03 | 93.5 |