Image-to-Text Retrieval on Flickr30k EN
86R@1AltCLIP
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| AltCLIPBackbone=ViT-L, Zero-shot=true, Stage=Contrastive Learning2022.11 | 86 | 98 | 99.1 | 90.4 | |
| AltCLIPTBackbone=ViT-L, Zero-shot=true, Stage=Teacher Learning2022.11 | 85.9 | 97.7 | 99.1 | 88.3 | |
| CLIPBackbone=ViT-L, Zero-shot=true2022.11 | 85.1 | 97.3 | 99.2 | 87.6 | |
| CN-CLIPBackbone=ViT-L, Zero-shot=true2022.11 | 66.5 | 91.2 | 96 | 77.3 | |
| TaiyiBackbone=ViT-L, Zero-shot=true2022.11 | 39.3 | 68.1 | 79.6 | 53.3 |