Text-to-Image Retrieval on MSCOCO EN
42.9R@1AltCLIP
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| AltCLIPBackbone=ViT-L, Zero-shot=true, Stage=Contrastive Learning2022.11 | 42.9 | 68 | 77.4 | 69.2 | |
| AltCLIPTBackbone=ViT-L, Zero-shot=true, Stage=Teacher Learning2022.11 | 37.5 | 62.1 | 72.1 | 66.1 | |
| CLIPBackbone=ViT-L, Zero-shot=true2022.11 | 36.5 | 61.1 | 71.1 | 65.2 | |
| CN-CLIPBackbone=ViT-L, Zero-shot=true2022.11 | 26.1 | 50 | 61.3 | 53.4 | |
| TaiyiBackbone=ViT-L, Zero-shot=true2022.11 | 11.7 | 27.8 | 37.4 | 32.2 |