Referring Image Segmentation on G-Ref u (test)
75.3mIoUDETRIS-L*
Evaluation results
| Method | Links | |
|---|---|---|
| DETRIS-L*Tuning Protocol=Parameter Efficient Tuning, Training Data Strategy=Mixed RefCOCO dataset, Model Scale=Large2025.01 | 75.3 | |
| UNINEXT-LTraining Data Strategy=Mixed RefCOCO dataset, Model Scale=Large2025.01 | 73.7 | |
| DETRIS-LTuning Protocol=Parameter Efficient Tuning, Model Scale=Large2025.01 | 70.2 | |
| PolyFormer-L*Training Data Strategy=Mixed RefCOCO dataset, Model Scale=Large2025.01 | 70.2 | |
| LISA-7BTuning Protocol=Traditional Full Fine-tuning, Model Scale=7B2025.01 | 68.5 | |
| DETRIS-BTuning Protocol=Parameter Efficient Tuning, Model Scale=Base2025.01 | 68.1 | |
| RISCLIP-BTuning Protocol=Traditional Full Fine-tuning, Model Scale=Base2025.01 | 68 | |
| MagNetTuning Protocol=Traditional Full Fine-tuning2025.01 | 66.2 | |
| ReLA (2023b)Tuning Protocol=Traditional Full Fine-tuning2025.01 | 66 | |
| ReLA (2023a)Tuning Protocol=Traditional Full Fine-tuning2025.01 | 66 | |
| CGFormerTuning Protocol=Traditional Full Fine-tuning2025.01 | 65.1 | |
| DMMITuning Protocol=Traditional Full Fine-tuning2025.01 | 64.2 | |
| ReMamberTuning Protocol=Traditional Full Fine-tuning2025.01 | 64 | |
| BarLeRIATuning Protocol=Parameter Efficient Tuning2025.01 | 63.8 | |
| CRISTuning Protocol=Traditional Full Fine-tuning2025.01 | 60.4 | |
| ETRISTuning Protocol=Parameter Efficient Tuning2025.01 | 59.9 |