Open-domain Visual Entity Recognition on OVEN-Wiki (test)
5.6Entity Split SEENCLIP ViT-L/14
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CLIP ViT-L/14# Params=0.42B, Training Type=Fine-tuned2023.02 | 5.6 | 4.9 | 1.3 | 2 | 2.4 | |
| CLIP2CLIP ViT-L/14# Params=0.86B, Training Type=Fine-tuned2023.02 | 12.6 | 10.5 | 3.8 | 3.2 | 5.3 | |
| PaLI-3B# Params=3B, Training Type=Fine-tuned2023.02 | 19.1 | 6 | 27.4 | 12 | 11.8 | |
| PaLI-17B# Params=17B, Training Type=Fine-tuned2023.02 | 28.3 | 11.2 | 36.2 | 21.7 | 20.2 | |
| CLIP Fusion ViT-L/14# Params=0.88B, Training Type=Fine-tuned2023.02 | 33.6 | 4.8 | 25.8 | 1.4 | 4.1 |