Metric: R@1 (higher is better)
| # | Model↕ | R@1▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | CN-CLIP (ViT-H/14) | 81.5 | No | Chinese CLIP: Contrastive Vision-Language Pretra... | 2022-11-02 | Code |
| 2 | CN-CLIP (ViT-L/14@336px) | 80.1 | No | Chinese CLIP: Contrastive Vision-Language Pretra... | 2022-11-02 | Code |
| 3 | R2D2 (ViT-L/14) | 79.1 | No | CCMB: A Large-scale Chinese Cross-modal Benchmark | 2022-05-08 | Code |
| 4 | CN-CLIP (ViT-L/14) | 78.9 | No | Chinese CLIP: Contrastive Vision-Language Pretra... | 2022-11-02 | Code |
| 5 | CN-CLIP (ViT-B/16) | 77 | No | Chinese CLIP: Contrastive Vision-Language Pretra... | 2022-11-02 | Code |
| 6 | R2D2 (ViT-B) | 75.1 | No | CCMB: A Large-scale Chinese Cross-modal Benchmark | 2022-05-08 | Code |
| 7 | Wukong (ViT-L/14) | 74 | No | Wukong: A 100 Million Large-scale Chinese Cross-... | 2022-02-14 | Code |
| 8 | Wukong (ViT-B/32) | 67 | No | Wukong: A 100 Million Large-scale Chinese Cross-... | 2022-02-14 | Code |
| 9 | CN-CLIP (RN50) | 66.8 | No | Chinese CLIP: Contrastive Vision-Language Pretra... | 2022-11-02 | Code |