Text-to-Image Retrieval on AIC-ICC
48.6R@1Wukong_ViT-L
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Wukong_ViT-LBackbone=ViT-L, Evaluation Protocol=Fine-tuned2022.02 | 48.6 | 72.5 | 80.2 | 71.6 | — | |
| CLIP_ViT-LBackbone=ViT-L, Evaluation Protocol=Fine-tuned2022.02 | 46.2 | 70.7 | 78.6 | 69.9 | — | |
| FILIP_ViT-LBackbone=ViT-L, Evaluation Protocol=Fine-tuned2022.02 | 44.9 | 69 | 77.5 | 67.4 | — | |
| FILIP_Swin-LBackbone=Swin-L, Evaluation Protocol=Fine-tuned2022.02 | 41.1 | 65.7 | 74.7 | 65.2 | — | |
| Wukong_Swin-LBackbone=Swin-L, Evaluation Protocol=Fine-tuned2022.02 | 38.6 | 64.1 | 73.6 | 63.7 | — | |
| CLIP_ViT-BBackbone=ViT-B, Evaluation Protocol=Fine-tuned2022.02 | 38.1 | 63.7 | 73.3 | 63.1 | — | |
| CLIP_Swin-LBackbone=Swin-L, Evaluation Protocol=Fine-tuned2022.02 | 37.3 | 62.8 | 72.7 | 63 | — | |
| Wukong_ViT-BBackbone=ViT-B, Evaluation Protocol=Fine-tuned2022.02 | 36.7 | 36.7 | 71.7 | 57 | — | |
| WenLan 2.0Evaluation Protocol=Fine-tuned2022.02 | 34.1 | 58.9 | 69.1 | 58.7 | — | |
| FILIP_ViT-BBackbone=ViT-B, Evaluation Protocol=Fine-tuned2022.02 | 32.9 | 58.4 | 68.8 | 57.6 | — | |
| ERNIE-ViL 2.0Setting=Zero-shot2022.09 | 19 | 35.3 | 43.5 | — | 40.6 | |
| R2D2Setting=Zero-shot2022.09 | 14.9 | 28.1 | 33.4 | — | 34.5 | |
| BriVLSetting=Zero-shot2022.09 | 14.4 | 30.4 | 39.1 | — | 31.1 |