Referring Image Segmentation on RefCOCO+ medium (test B)
61.81oIoUMagNet+
Evaluation results
| Method | Links | |
|---|---|---|
| MagNet+Backbone=Swin-B, Training Setting=Multiple Datasets2023.12 | 61.81 | |
| PolyFormerBackbone=Swin-B, Training Setting=Multiple Datasets2023.12 | 59.33 | |
| MagNetBackbone=Swin-B, Training Setting=Single Dataset2023.12 | 58.14 | |
| ReLABackbone=Swin-B, Training Setting=Single Dataset2023.12 | 57.65 | |
| PVDBackbone=Swin-B, Training Setting=Single Dataset2023.12 | 56.92 | |
| CoupAlignBackbone=Swin-B, Training Setting=Single Dataset2023.12 | 56.69 | |
| MCRESBackbone=Swin-B, Training Setting=Single Dataset2023.12 | 56.64 | |
| LISA-7BBackbone=SAM-H, Training Setting=Multiple Datasets2023.12 | 56.5 | |
| SADLRBackbone=Swin-B, Training Setting=Single Dataset2023.12 | 55.19 | |
| LAVTBackbone=Swin-B, Training Setting=Single Dataset2023.12 | 55.1 | |
| CRISBackbone=ResNet-101, Training Setting=Single Dataset2023.12 | 53.68 | |
| VLTBackbone=Darknet-53, Training Setting=Single Dataset2023.12 | 49.36 | |
| ReSTRBackbone=ViT-B-16, Training Setting=Single Dataset2023.12 | 48.27 |