Image-to-Text Retrieval on SV-10k
90.3R@1FLAIR
Evaluation results
| Method | Links | |
|---|---|---|
| FLAIRData=30M, Zero-shot=true, Vision Encoder=ViT-B/162024.12 | 90.3 | |
| FLAIRData=15M, Zero-shot=true, Vision Encoder=ViT-B/162024.12 | 88.8 | |
| FLAIRData=12M, Zero-shot=true, Vision Encoder=ViT-B/162024.12 | 85 | |
| SigLIPData=10B, Zero-shot=true, Vision Encoder=ViT-B/162024.12 | 83.4 | |
| LoTLIPData=100M, Zero-shot=true, Vision Encoder=ViT-B/162024.12 | 81.4 | |
| Long-CLIPData=400M, Zero-shot=true, Vision Encoder=ViT-B/162024.12 | 73.1 | |
| FLAIRData=3M, Zero-shot=true, Vision Encoder=ViT-B/162024.12 | 72 | |
| OpenCLIPData=2B, Zero-shot=true, Vision Encoder=ViT-B/162024.12 | 69.6 | |
| ALIGNData=700M, Zero-shot=true, Vision Encoder=ViT-B/162024.12 | 65.1 | |
| LiTData=100M, Zero-shot=true, Vision Encoder=ViT-B/162024.12 | 61.4 |