Referring Expression Segmentation on refCOCOg UMD (test)
75.2mIoUGETok-R1
Evaluation results
| Method | Links | |
|---|---|---|
| GETok-R1Training Mask Dec.=false, Learning Protocol=Reinforcement Learning2025.12 | 75.2 | |
| GETok-R1-gridTraining Mask Dec.=false, Learning Protocol=Reinforcement Learning2025.12 | 73.9 | |
| SAM-R1Training Mask Dec.=false, Learning Protocol=Reinforcement Learning2025.12 | 73.1 | |
| Seg-ZeroTraining Mask Dec.=false, Learning Protocol=Reinforcement Learning2025.12 | 72.6 | |
| VisionReasonerTraining Mask Dec.=false, Learning Protocol=Reinforcement Learning2025.12 | 72.2 | |
| GETok-SFT-gridTraining Mask Dec.=false, Learning Protocol=Supervised Fine-Tuning2025.12 | 70.9 | |
| GETok-SFTTraining Mask Dec.=false, Learning Protocol=Supervised Fine-Tuning2025.12 | 70.9 | |
| PixelLMTraining Mask Dec.=true, Learning Protocol=Supervised Fine-Tuning2025.12 | 70.5 | |
| LISATraining Mask Dec.=true, Learning Protocol=Supervised Fine-Tuning2025.12 | 70.5 | |
| Qwen2.5-VL-7BTraining Mask Dec.=false, Learning Protocol=Supervised Fine-Tuning2025.12 | 69.9 | |
| ReLATraining Mask Dec.=true, Learning Protocol=Supervised Fine-Tuning2025.12 | 66 | |
| LAVTTraining Mask Dec.=true, Learning Protocol=Supervised Fine-Tuning2025.12 | 62.1 | |
| CRISTraining Mask Dec.=true, Learning Protocol=Supervised Fine-Tuning2025.12 | 60.4 |