Image-Text Retrieval on MSCOCO
66.7MRCLIP
Evaluation Results
| Method | Links | |
|---|---|---|
| CLIPModel scale=0.4B, Zero-shot evaluation=true2024.01 | 66.7 | |
| AltCLIPModel scale=0.8B, Zero-shot evaluation=true2024.01 | 69.2 | |
| EVAModel scale=1.1B, Zero-shot evaluation=true2024.01 | 70.8 | |
| ALIGNModel scale=0.8B, Zero-shot evaluation=true2024.01 | 70.9 | |
| FILIPModel scale=0.4B, Zero-shot evaluation=true2024.01 | 72 | |
| ERNIE-ViL 2.0Zero-shot evaluation=true2024.01 | 73 | |
| CoCaModel scale=0.4B, Zero-shot evaluation=true2024.01 | 73.3 | |
| BEIT3Model scale=0.7B, Zero-shot evaluation=true2024.01 | 74.6 | |
| OpenCLIPModel scale=1.3B, Zero-shot evaluation=true2024.01 | 74.6 | |
| CoCaModel scale=0.8B, Zero-shot evaluation=true2024.01 | 74.7 | |
| M2-EncoderModel scale=0.4B, Zero-shot evaluation=true2024.01 | 75.2 | |
| CoCaModel scale=2.1B, Zero-shot evaluation=true2024.01 | 75.3 | |
| OpenCLIPModel scale=2.5B, Zero-shot evaluation=true2024.01 | 76 | |
| EVAModel scale=5.0B, Zero-shot evaluation=true2024.01 | 76.4 | |
| M2-EncoderModel scale=1B, Zero-shot evaluation=true2024.01 | 76.9 | |
| UMG-CLIPModel scale=0.4B, Zero-shot evaluation=true2024.01 | 78.5 | |
| UMG-CLIPModel scale=5B, Zero-shot evaluation=true2024.01 | 80.2 | |
| M2-EncoderModel scale=10B, Zero-shot evaluation=true2024.01 | 81.4 |