Image Search on COCO
76Recall@1BEIT-3
Evaluation results
| Method | Links | ||
|---|---|---|---|
| BEIT-3protocol=finetuned, averaging=average of top-1 image-to-text and text-to-image2022.08 | 76 | — | |
| Florenceprotocol=finetuned, averaging=average of top-1 image-to-text and text-to-image2022.08 | 72.5 | — | |
| Uni-Perceiver-v2 LARGEparameters=446M, task-specific fine-tuning=false2022.11 | 58.5 | — | |
| Uni-Perceiver-v2 BASEparameters=308M, task-specific fine-tuning=false2022.11 | 55.6 | — | |
| Uni-Perceiver-MOE LARGEparameters=505M, task-specific fine-tuning=false2022.11 | 55.3 | — | |
| Uni-Perceiver LARGEparameters=354M, task-specific fine-tuning=false2022.11 | 54.1 | — | |
| Uni-Perceiver-MOE BASEparameters=167M, task-specific fine-tuning=false2022.11 | 51.6 | — | |
| Uni-Perceiver BASEparameters=124M, task-specific fine-tuning=false2022.11 | 50.7 | — | |
| Flamingo-3Bparameters=3.2B, task-specific fine-tuning=false2022.11 | 48 | — | |
| 2WayNet2016.08 | 39.7 | 63.3 | |
| NLBD2016.08 | 39.6 | 75.2 | |
| VQA-A2016.08 | 37 | 70.9 | |
| m-CNN2016.08 | 32.6 | 68.6 | |
| RNN-FV2016.08 | 30.2 | 65 | |
| m-RNN2016.08 | 29 | 42.2 | |
| BRNN2016.08 | 27.4 | 60.2 | |
| CCA2016.08 | 25.1 | 59.8 |