Image-Text Retrieval on Flickr30K
90.1MRCLIP
Evaluation Results
| Method | Links | |
|---|---|---|
| CLIPModel scale=0.4B, Zero-shot evaluation=true2024.01 | 90.1 | |
| AltCLIPModel scale=0.8B, Zero-shot evaluation=true2024.01 | 90.4 | |
| EVAModel scale=1.1B, Zero-shot evaluation=true2024.01 | 90.9 | |
| ALIGNModel scale=0.8B, Zero-shot evaluation=true2024.01 | 92.2 | |
| FILIPModel scale=0.4B, Zero-shot evaluation=true2024.01 | 92.3 | |
| CoCaModel scale=0.4B, Zero-shot evaluation=true2024.01 | 92.6 | |
| ERNIE-ViL 2.0Zero-shot evaluation=true2024.01 | 92.9 | |
| OpenCLIPModel scale=1.3B, Zero-shot evaluation=true2024.01 | 93.1 | |
| CoCaModel scale=0.8B, Zero-shot evaluation=true2024.01 | 93.7 | |
| EVAModel scale=5.0B, Zero-shot evaluation=true2024.01 | 93.8 | |
| OpenCLIPModel scale=2.5B, Zero-shot evaluation=true2024.01 | 93.9 | |
| CoCaModel scale=2.1B, Zero-shot evaluation=true2024.01 | 94.3 | |
| M2-EncoderModel scale=0.4B, Zero-shot evaluation=true2024.01 | 94.5 | |
| UMG-CLIPModel scale=5B, Zero-shot evaluation=true2024.01 | 94.6 | |
| BEIT3Model scale=0.7B, Zero-shot evaluation=true2024.01 | 94.9 | |
| UMG-CLIPModel scale=0.4B, Zero-shot evaluation=true2024.01 | 95 | |
| M2-EncoderModel scale=1B, Zero-shot evaluation=true2024.01 | 95.4 | |
| M2-EncoderModel scale=10B, Zero-shot evaluation=true2024.01 | 96.9 |