In-Context Object Localization on GOT-10k
82.6mIoUFOCUS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FOCUSShots=4-shot2026.05 | 82.6 | — | |
| FOCUSShots=2-shot2026.05 | 80.6 | — | |
| FOCUSShots=1-shot2026.05 | 77.1 | — | |
| IPLoc (7B)Shots=4-shot2026.05 | 68.7 | — | |
| IPLoc (7B)Shots=2-shot2026.05 | 68.1 | — | |
| InternVL2-76BShots=2-shot2026.05 | 66.7 | — | |
| InternVL2-76BShots=1-shot2026.05 | 65.8 | — | |
| InternVL2-76BShots=4-shot2026.05 | 65.4 | — | |
| IPLoc (7B)Shots=1-shot2026.05 | 64.2 | — | |
| Qwen2-VL-72BShots=1-shot2026.05 | 62.7 | — | |
| Qwen2-VL-72BShots=2-shot2026.05 | 60.1 | — | |
| Qwen2-VL-72BShots=4-shot2026.05 | 59.9 | — | |
| Qwen2-VL-7BShots=4-shot2026.05 | 39.3 | — | |
| Qwen2-VL-7BShots=2-shot2026.05 | 37 | — | |
| Qwen2-VL-7BShots=1-shot2026.05 | 36.2 | — | |
| LLaVA-OVShots=4-shot2026.05 | 33.7 | — | |
| Idefics3Shots=4-shot2026.05 | 32.3 | — | |
| LLaVA-OVShots=2-shot2026.05 | 26.4 | — | |
| Pixtral-12BShots=4-shot2026.05 | 23.7 | — | |
| Idefics3Shots=2-shot2026.05 | 21.2 | — | |
| Pixtral-12BShots=2-shot2026.05 | 19.4 | — | |
| LLaVA-OVShots=1-shot2026.05 | 18.6 | — | |
| Pixtral-12BShots=1-shot2026.05 | 13.9 | — | |
| Idefics3Shots=1-shot2026.05 | 9.3 | — | |
| FOCUSShots=Overall2026.05 | — | 67.7 | |
| Idefics3Shots=Overall2026.05 | — | 15.2 | |
| InternVL2-76BShots=Overall2026.05 | — | 56.1 | |
| IPLoc (7B)Shots=Overall2026.05 | — | 58.8 | |
| LLaVA-OVShots=Overall2026.05 | — | 23 | |
| Pixtral-12BShots=Overall2026.05 | — | 15.5 | |
| Qwen2-VL-72BShots=Overall2026.05 | — | 55 | |
| Qwen2-VL-7BShots=Overall2026.05 | — | 31.1 |