Referring Expression Segmentation on G-Ref (val)
62.84cIoUMABP
Evaluation results
| Method | Links | |
|---|---|---|
| MABPVisual Encoder=Swin-B, Textual Encoder=BERT2024.05 | 62.84 | |
| VLTVisual Encoder=Swin-B, Textual Encoder=BERT2024.05 | 62.8 | |
| ReLAVisual Encoder=Swin-B, Textual Encoder=BERT2024.05 | 62.7 | |
| CGFormerVisual Encoder=Swin-B, Textual Encoder=BERT2024.05 | 62.51 | |
| BKINetVisual Encoder=CLIP-R 101, Textual Encoder=CLIP2024.05 | 61.64 | |
| LAVTVisual Encoder=Swin-B, Textual Encoder=BERT2024.05 | 60.5 | |
| ReSTRVisual Encoder=ViT-B, Textual Encoder=Transformer2024.05 | 54.48 | |
| VLTVisual Encoder=Darknet53, Textual Encoder=bi-GRU2024.05 | 49.76 |