Referring Image Segmentation on G-Ref UMD (val)
66.98oIoUASDA
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| ASDAMRaCL=true2026.03 | 66.98 | — | — | — | |
| ASDAMRaCL=false2026.03 | 65.71 | — | — | — | |
| DETRISMRaCL=true2026.03 | 64.94 | — | — | — | |
| DETRISMRaCL=false2026.03 | 64.29 | — | — | — | |
| LAVTMRaCL=true2026.03 | 63.93 | — | — | — | |
| DMMIMRaCL=true2026.03 | 63.24 | — | — | — | |
| DMMIMRaCL=false2026.03 | 61.75 | — | — | — | |
| LAVTMRaCL=false2026.03 | 61.24 | — | — | — | |
| CRISMRaCL=true2026.03 | 58.05 | — | — | — | |
| CRISMRaCL=false2026.03 | 55.91 | — | — | — | |
| CRISVisual Encoder=CLIP-R101, Textual Encoder=CLIP2023.06 | — | — | — | 59.87 | |
| LAVTVisual Encoder=Swin-B, Textual Encoder=BERT2023.06 | — | — | — | 61.24 | |
| MCNVisual Encoder=Darknet53, Textual Encoder=bi-GRU2023.06 | — | — | — | 49.22 | |
| ReLAVisual Encoder=Swin-B, Textual Encoder=BERT2023.06 | — | — | — | 65 | |
| VLT [5]Visual Encoder=Darknet53, Textual Encoder=bi-GRU2023.06 | — | — | — | 54.96 | |
| VLT [6]Visual Encoder=Swin-B, Textual Encoder=BERT2023.06 | — | — | — | 63.49 |