Referring Expression Segmentation on G-Ref UMD (test)
66.22cIoUVLT [6]
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| VLT [6]Visual Encoder=Swin-B, Textual Encoder=BERT2023.06 | 66.22 | — | — | |
| VLT+Visual Encoder=Swin-B, Textual Encoder=BERT2026.01 | 66.22 | — | — | |
| ReLAVisual Encoder=Swin-B, Textual Encoder=BERT2023.06 | 65.97 | — | — | |
| ReLAVisual Encoder=Swin-B, Textual Encoder=BERT, Metric Mode=cIoU2026.01 | 65.97 | — | — | |
| LAVTVisual Encoder=Swin-B, Textual Encoder=BERT2023.06 | 62.09 | — | — | |
| LAVTVisual Encoder=Swin-B, Textual Encoder=BERT2026.01 | 62.09 | — | — | |
| CRISVisual Encoder=CLIP-R101, Textual Encoder=CLIP2023.06 | 60.36 | — | — | |
| CRISVisual Encoder=CLIP, Textual Encoder=CLIP2026.01 | 60.36 | — | — | |
| VLT [5]Visual Encoder=Darknet53, Textual Encoder=bi-GRU2023.06 | 57.73 | — | — | |
| VLTVisual Encoder=Darknet53, Textual Encoder=GRU2026.01 | 57.73 | — | — | |
| VLT2021.08 | 56.65 | — | 60.24 | |
| LTSVisual Encoder=Darknet53, Textual Encoder=GRU2026.01 | 54.25 | — | — | |
| CGAN2021.08 | 51.69 | — | — | |
| MCNVisual Encoder=Darknet53, Textual Encoder=bi-GRU2023.06 | 49.4 | — | — | |
| MCNVisual Encoder=Darknet53, Textual Encoder=GRU2026.01 | 49.4 | — | — | |
| MCN2021.08 | 49.4 | — | — | |
| MAttNet2021.08 | 48.61 | — | — | |
| ReLAVisual Encoder=Swin-B, Textual Encoder=BERT, Metric Mode=mIoU2026.01 | — | 69.56 | — |