| { | |
| "flickr30k_test_t2i": { | |
| "R@1": 0.432, | |
| "R@5": 0.74, | |
| "R@10": 0.836, | |
| "gallery": 1000, | |
| "task": "text-to-image retrieval in the fusion-embedding-2 text space" | |
| }, | |
| "comparison": { | |
| "dinov2_backbone_same_recipe": {"R@1": 0.318, "R@5": 0.613, "R@10": 0.749}, | |
| "note": "Same projector recipe trained on a frozen DINOv2 backbone instead of MoonViT-V2." | |
| }, | |
| "training": {"n_train": 6000, "steps": 4000, "runtime_s": 505.4, "gpu": "A100-80GB"} | |
| } | |