Zero Shot Composed Image Retrieval Zs Cir On
Metriken
mAP@10
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | mAP@10 |
|---|---|
| isearle-improving-textual-inversion-for-zero | 10.94 |
| semantic-editing-increment-benefits-zero-shot | 37.23 |
| isearle-improving-textual-inversion-for-zero | 11.24 |
| magiclens-self-supervised-image-retrieval | 23.8 |
| compodiff-versatile-composed-image-retrieval | 17.71 |
| context-i2w-mapping-images-to-context | 14.62 |
| ldre-llm-based-divergent-reasoning-and | 24.03 |
| language-only-efficient-training-of-zero-shot | 21.01 |
| collm-a-large-language-model-for-composed | 20.4 |
| vision-by-language-for-training-free | 15.42 |
| pic2word-mapping-pictures-to-words-for-zero | 9.51 |
| covr-learning-composed-video-retrieval-from | 29.55 |
| reason-before-retrieve-one-stage-reflective | 25.33 |
| pretrain-like-you-inference-masked-tuning | 8.03 |
| semantic-editing-increment-benefits-zero-shot | 25.82 |
| pretrain-like-you-inference-masked-tuning | 11.63 |
| magiclens-self-supervised-image-retrieval | 32.0 |
| reason-before-retrieve-one-stage-reflective | 31.14 |
| megapairs-massive-data-synthesis-for | 35.0 |
| this-is-my-unicorn-fluffy-personalizing | 5.32 |
| magiclens-self-supervised-image-retrieval | 35.4 |
| zero-shot-composed-image-retrieval-with | 12.73 |
| compodiff-versatile-composed-image-retrieval | 13.51 |
| reducing-task-discrepancy-of-text-encoders | 18.11 |
| ldre-llm-based-divergent-reasoning-and | 18.32 |
| vision-by-language-for-training-free | 19.01 |
| megapairs-massive-data-synthesis-for | 40.2 |
| imagine-and-seek-improving-composed-image | 27.41 |
| ldre-llm-based-divergent-reasoning-and | 32.24 |
| magiclens-self-supervised-image-retrieval | 30.8 |
| reducing-task-discrepancy-of-text-encoders | 22.29 |
| isearle-improving-textual-inversion-for-zero | 12.67 |
| vision-by-language-for-training-free | 27.59 |
| semantic-editing-increment-benefits-zero-shot | 33.77 |
| imagine-and-seek-improving-composed-image | 34.26 |
| imagescope-unifying-language-guided-image-1 | 28.36 |
| language-only-efficient-training-of-zero-shot | 13.58 |
| zero-shot-composed-image-retrieval-with | 9.94 |
| collm-a-large-language-model-for-composed | 20.8 |
| isearle-improving-textual-inversion-for-zero | 13.61 |
| megapairs-massive-data-synthesis-for | 43.4 |
| reason-before-retrieve-one-stage-reflective | 19.17 |