Referring Remote Sensing Image Segmentation on RefSegRS (val)
96.29Pr@0.5RemoteSAM
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| RemoteSAMVisual Encoder=Swin-B, Text Encoder=BERT2026.05 | 96.29 | 93.97 | 84.69 | 45.71 | 8.35 | 82.69 | 77.31 | |
| ICIPNetVisual Encoder=Swin-B, Text Encoder=BERT2026.05 | 96.23 | 93.93 | 87.4 | 51.81 | 9.54 | 83.78 | 78.25 | |
| MAFNVisual Encoder=Swin-B, Text Encoder=BERT2026.05 | 95.59 | 91.18 | 82.37 | 45.48 | 8.35 | 82.04 | 76.53 | |
| FIANetVisual Encoder=Swin-B, Text Encoder=BERT2026.05 | 94.9 | 92.81 | 84.22 | 47.33 | 9.98 | 82.51 | 77.18 | |
| CroBIM-UVisual Encoder=ConvNeXt-B, Text Encoder=BERT2026.01 | 94.11 | 88.54 | 68.45 | 27.22 | 6.57 | 78.03 | 72.55 | |
| CroBIMVisual Encoder=ConvNeXt-B, Text Encoder=BERT2026.01 | 93.04 | 87.7 | 66.13 | 26.91 | 5.8 | 77.95 | 71.93 | |
| RMSINVisual Encoder=Swin-B, Text Encoder=BERT2026.05 | 93.04 | 88.4 | 77.26 | 33.87 | 7.42 | 81.58 | 74.06 | |
| CroBIMVisual Encoder=Swin-B, Text Encoder=BERT2026.01 | 87.24 | 75.17 | 44.78 | 19.03 | 6.26 | 78.85 | 65.79 | |
| RIS-DMMIVisual Encoder=Swin-B, Text Encoder=BERT2026.01 | 86.17 | 74.71 | 38.05 | 18.1 | 3.25 | 74.02 | 65.72 | |
| robust-ref-segVisual Encoder=Swin-B, Text Encoder=BERT2026.01 | 81.67 | 52.44 | 30.86 | 17.17 | 5.8 | 77.74 | 60.44 | |
| LAVTVisual Encoder=Swin-B, Text Encoder=BERT2026.01 | 80.97 | 58.7 | 31.09 | 15.55 | 4.64 | 78.5 | 61.53 | |
| LGCEVisual Encoder=Swin-B, Text Encoder=BERT2026.01 | 79.81 | 54.29 | 29.7 | 15.31 | 5.1 | 78.24 | 60.66 | |
| CARISVisual Encoder=Swin-B, Text Encoder=BERT2026.01 | 68.45 | 47.1 | 25.52 | 14.62 | 3.71 | 75.79 | 54.3 | |
| RMSINVisual Encoder=Swin-B, Text Encoder=BERT2026.01 | 68.21 | 46.64 | 24.13 | 13.69 | 3.25 | 74.4 | 54.24 | |
| CrossVLTVisual Encoder=Swin-B, Text Encoder=BERT2026.01 | 67.52 | 43.85 | 25.99 | 14.62 | 1.87 | 76.12 | 55.27 | |
| LSCMVisual Encoder=ResNet-101, Text Encoder=LSTM2026.01 | 56.82 | 41.24 | 21.85 | 12.11 | 2.51 | 62.82 | 40.59 | |
| RRNVisual Encoder=ResNet-101, Text Encoder=LSTM2026.01 | 55.43 | 42.98 | 23.11 | 13.72 | 2.64 | 69.24 | 50.81 | |
| ETRISVisual Encoder=ResNet-101, Text Encoder=CLIP2026.01 | 54.99 | 35.03 | 25.06 | 12.53 | 1.62 | 72.89 | 54.03 | |
| CRISVisual Encoder=ResNet-101, Text Encoder=CLIP2026.01 | 53.13 | 36.19 | 24.36 | 11.83 | 2.55 | 72.14 | 53.74 | |
| BKINetVisual Encoder=ResNet-101, Text Encoder=CLIP2026.01 | 52.04 | 35.31 | 18.35 | 12.78 | 1.23 | 75.37 | 56.12 | |
| MAttNetVisual Encoder=ResNet-101, Text Encoder=LSTM2026.01 | 48.56 | 40.26 | 20.59 | 12.98 | 2.02 | 66.84 | 41.73 | |
| CMSAVisual Encoder=ResNet-101, Text Encoder=None2026.01 | 39.24 | 38.44 | 20.39 | 11.79 | 1.52 | 63.84 | 43.62 | |
| BRINetVisual Encoder=ResNet-101, Text Encoder=LSTM2026.01 | 36.86 | 35.53 | 19.93 | 10.66 | 2.84 | 61.59 | 38.73 |