Semantic Segmentation on SWJTU-Vision-Language
69.73Overall Accuracy (OA)TSMNet
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| TSMNetModality=Multimodal2026.04 | 69.73 | 48.83 | 76.48 | 61.18 | 55.2 | 80.09 | 84.82 | 69.93 | 39.49 | |
| DenseCLIPModality=Multimodal, Supervision=Text Supervision2026.04 | 68.09 | 47.44 | 77.17 | 57.47 | 56.8 | 79.53 | 83.11 | 69.91 | 29.65 | |
| MSSNetModality=Multimodal2026.04 | 65.68 | 37.49 | 74.12 | 58.66 | 32.95 | 78.17 | 62.9 | 25.87 | 12.52 | |
| TACOSSModality=Multimodal, Supervision=Text Supervision2026.04 | 65.43 | 42.64 | 74.97 | 58.82 | 39.28 | 73.32 | 65.56 | 44.86 | 20.56 | |
| Deeplab v3+Modality=Single-modality2026.04 | 65.34 | 37.12 | 63.76 | 52.68 | 51.28 | 72.75 | 80.84 | 58.07 | 38.04 | |
| CMGFNetModality=Multimodal2026.04 | 64.93 | 34.7 | 63.98 | 59.23 | 50.78 | 76.24 | 74.32 | 66.76 | 32.28 | |
| DDHRNetModality=Multimodal2026.04 | 62.63 | 32.66 | 62.83 | 54.65 | 50.93 | 79.59 | 81.42 | 56.33 | 33.71 | |
| MCANetModality=Multimodal2026.04 | 61.42 | 33.5 | 61.03 | 60.02 | 38.31 | 73.06 | 65.13 | 33.82 | 39.48 |