Object Counting Ranking on COCO-REM 2-imgs
0.893Kendall's TauQwen2.5-VL-7B + RARL
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2.5-VL-7B + RARLBackbone=Qwen2.5-VL-7B, Training Strategy=RARL2026.01 | 0.893 | |
| Qwen2.5-VL-3B + RARLBackbone=Qwen2.5-VL-3B, Training Strategy=RARL2026.01 | 0.831 | |
| Qwen2.5-VL-3B + SFTBackbone=Qwen2.5-VL-3B, Training Strategy=SFT2026.01 | 0.765 | |
| Qwen2.5-VL-7B + SFTBackbone=Qwen2.5-VL-7B, Training Strategy=SFT2026.01 | 0.745 | |
| Qwen2.5-VL-3BBackbone=Qwen2.5-VL-3B, Training Strategy=Base2026.01 | 0.744 | |
| Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B, Training Strategy=Base2026.01 | 0.736 |