Image-Text Retrieval on MS COCO
52.7Recall@1SigLIP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SigLIPResolution=384, Pre-training Dataset=WebLi, Evaluation Protocol=Zero-shot2024.12 | 52.7 | — | |
| SigLIPResolution=256, Pre-training Dataset=WebLi, Evaluation Protocol=Zero-shot2024.12 | 51.1 | — | |
| EVA-02-CLIPResolution=336, Pre-training Dataset=Merged-2B, Evaluation Protocol=Zero-shot2024.12 | 47.9 | — | |
| DFNResolution=224, Pre-training Dataset=DFN-2B, Evaluation Protocol=Zero-shot2024.12 | 47 | — | |
| OpenCLIPResolution=224, Pre-training Dataset=LAION-2B, Evaluation Protocol=Zero-shot2024.12 | 46.1 | — | |
| MetaCLIPResolution=224, Pre-training Dataset=MetaCLIP-2.5B, Evaluation Protocol=Zero-shot2024.12 | 45.5 | — | |
| dino.txtResolution=224, Pre-training Dataset=LVTD-2.3B, Evaluation Protocol=Zero-shot2024.12 | 45.4 | — | |
| dino.txtResolution=336, Pre-training Dataset=LVTD-2.3B, Evaluation Protocol=Zero-shot2024.12 | 44.9 | — | |
| CLIPResolution=336, Pre-training Dataset=WIT-400M, Evaluation Protocol=Zero-shot2024.12 | 37.1 | — | |
| CLIPSetting=Zero-shot2026.02 | — | 59.7 | |
| iBOTSetting=Zero-shot2026.02 | — | 29.38 | |
| MAESetting=Zero-shot2026.02 | — | 13.46 | |
| STELLARSetting=Zero-shot2026.02 | — | 22.34 |