Image-to-Text Generation on MS-COCO 5% 2014 (test val)
25.5CLIP Similarity (CLIP)
GIT-large
Updated 2d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.05 | 25.5 | -0.0043 | -0.2593 | 86.49 | 64.59 | -0.219 | |
2026.05 | 25.11 | -0.0021 | -0.2532 | 86.2 | 64.74 | -0.2146 | |
2026.05 | 24.53 | -0.0074 | -0.2527 | 81.06 | 56.31 | -0.2475 | |
2026.05 | 23.3 | 0.007 | -0.226 | 83.49 | 63.35 | -0.2014 |