Image-to-Text Retrieval on XTD
97.7Retrieval Score (ES)InternVL-G
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| InternVL-Gzero-shot=true2023.12 | 97.7 | 98.6 | 96.5 | 96.7 | 96.9 | 95.1 | 94.8 | 96.1 | 96.6 | |
| OpenCLIP-XLM-R-Hzero-shot=true2023.12 | 96.1 | 97.3 | 94.5 | 94.7 | 96 | 90.2 | 93.9 | 94 | 94.6 | |
| InternVL-Czero-shot=true2023.12 | 95.7 | 97.3 | 95.1 | 95.6 | 96 | 92.2 | 93.3 | 95.5 | 95.1 | |
| OpenCLIP-XLM-R-Bzero-shot=true2023.12 | 94.4 | 95.8 | 92.5 | 91.8 | 94.4 | 86.3 | 89.9 | 90.7 | 92 | |
| AltCLIPzero-shot=true2023.12 | 94.1 | 95.4 | 92.9 | 95.1 | 94.2 | 94.4 | 91.8 | 91.7 | 93.7 | |
| MURALzero-shot=true2023.12 | 92.9 | — | — | 89.7 | 91.8 | 88.1 | 87.2 | — | — | |
| M-CLIPzero-shot=true2023.12 | 91 | 92.4 | 90 | 89.7 | 91.1 | 85.2 | 85.8 | 81.9 | 88.4 | |
| mUSE m3zero-shot=true2023.12 | 78.9 | 85.3 | 78.9 | 76.7 | 73.6 | 67.8 | 76.1 | 70.7 | 76 |