Composed Image Retrieval on ImageNet-R (test)
23.77Cartoon R@10FREEDOM
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| FREEDOMSource domain=PHOTO2024.12 | 23.77 | 48.83 | 32.84 | 42.82 | 25.7 | 47.59 | 27.86 | 48.96 | 27.54 | 47.05 | |
| CIReVLSource domain=PHOTO2024.12 | 19.2 | 42.8 | 22.2 | 43.1 | 30.2 | 41.3 | 23.4 | 45 | 23.75 | 43.05 | |
| KEDsSource domain=PHOTO2024.12 | 14.8 | 34.2 | 23.5 | 34.8 | 16.5 | 36.3 | 17.4 | 36.4 | 18 | 35.4 | |
| MagicLensSource domain=PHOTO2024.12 | 13.65 | 31.31 | 6.59 | 19.21 | 14.8 | 31.79 | 10.33 | 24.82 | 11.34 | 26.78 | |
| CompoDiffText Encoder=CLIP, Source domain=PHOTO2024.12 | 13.21 | 24.06 | 17.03 | 26.17 | 11.22 | 26.25 | 11.24 | 22.96 | 13.18 | 24.86 | |
| CompoDiffText Encoder=CLIP+T5-XL, Source domain=PHOTO2024.12 | 12.91 | 24.4 | 17.22 | 26.4 | 11.57 | 26.11 | 11.53 | 22.54 | 13.31 | 24.86 | |
| WeiComSource domain=PHOTO2024.12 | 11.61 | 24.36 | 15.24 | 23.72 | 8 | 17.89 | 13.81 | 26.18 | 12.17 | 23.04 | |
| ARTEMISTraining dataset=CompoDiff dataset, Source domain=PHOTO2024.12 | 11.42 | 23.81 | 15.49 | 25.44 | 11.21 | 24.01 | 10.84 | 21.07 | 12.24 | 23.58 | |
| CLIP4CirTraining dataset=CompoDiff dataset, Source domain=PHOTO2024.12 | 10.9 | 24.12 | 16.08 | 25.6 | 11.01 | 23.57 | 10.45 | 21.86 | 12.11 | 23.79 | |
| SEARLESource domain=PHOTO2024.12 | 10.17 | 30.32 | 17.02 | 32 | 8.23 | 9.1 | 11.6 | 32.41 | 11.76 | 30.96 | |
| MagicLensPrompt type=original prompt, Source domain=PHOTO2024.12 | 9.95 | 22.37 | 5.07 | 17.58 | 11.51 | 26.76 | 7.92 | 19.7 | 8.61 | 21.6 | |
| CompoDiffText Encoder=T5-XL, Source domain=PHOTO2024.12 | 8.43 | 20.4 | 15.73 | 25.69 | 11.19 | 22.48 | 9.19 | 18.45 | 11.14 | 21.76 | |
| Pic2WordTraining dataset=LAION 2B-en, Source domain=PHOTO2024.12 | 8.17 | 20.86 | 14.08 | 25.06 | 8.73 | 22.07 | 10.43 | 23.63 | 10.35 | 22.91 | |
| Pic2WordSource domain=PHOTO2024.12 | 8 | 21.9 | 13.5 | 25.6 | 8.7 | 21.6 | 10 | 23.8 | 10.05 | 23.23 | |
| Pic2WordTraining dataset=CC-3M, Source domain=PHOTO2024.12 | 7.35 | 18.53 | 12.79 | 25.54 | 10.39 | 22.96 | 10.24 | 23.76 | 10.19 | 22.7 | |
| Text + ImageSource domain=PHOTO2024.12 | 1.96 | 12.91 | 2.18 | 10.68 | 1.34 | 9.89 | 1.82 | 12.15 | 1.83 | 11.41 | |
| SEARLEPrompt type=default, Source domain=PHOTO2024.12 | 1.49 | 12.38 | 3.78 | 13.88 | 1.99 | 15.34 | 2.18 | 15.34 | 2.36 | 14.24 | |
| ImageSource domain=PHOTO2024.12 | 0.31 | 4.51 | 0.21 | 1.73 | 0.54 | 5.65 | 0.33 | 4.04 | 0.35 | 3.98 | |
| TextSource domain=PHOTO2024.12 | 0.15 | 0.95 | 0.87 | 3.73 | 0.71 | 1.77 | 0.36 | 1.89 | 0.52 | 2.09 |