Semantic Segmentation on LoveDA (Detailed Class Metrics)
62.97mIoUSemiEarth
Evaluation results
| Method | Links | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| SemiEarthRatio=10%2026.01 | 62.97 | 71.1 | 60.24 | 64.87 | 62.44 | 76.7 | 42.42 | 63.05 | — | — | — | — | — | — | — | — | — | |
| SemiEarthRatio=5%2026.01 | 61.34 | 69.57 | 57.7 | 62.12 | 60.52 | 75.61 | 42.88 | 60.98 | — | — | — | — | — | — | — | — | — | |
| SemiEarthRatio=1%2026.01 | 56.25 | 64.99 | 57.12 | 56.89 | 56.86 | 73.17 | 25.69 | 59.03 | — | — | — | — | — | — | — | — | — | |
| Dynamic Dictionary Learning2025.03 | 55.3 | 47.6 | 61.2 | 59.1 | 81.6 | 23.8 | 48.8 | 64.8 | — | — | — | — | — | — | — | — | — | |
| SFA-Net2025.03 | 54.9 | 48.4 | 60.3 | 59.1 | 81.9 | 24.1 | 46.2 | 64 | — | — | — | — | — | — | — | — | — | |
| UperNetbackbone=ViT-G12x42023.04 | 54.4 | 47.57 | 61.6 | 59.91 | 81.79 | 18.6 | 47.3 | 64 | — | — | — | — | — | — | — | — | — | |
| AerialFormer2025.03 | 54.1 | 47.8 | 60.7 | 59.3 | 81.5 | 17.9 | 47.9 | 64 | — | — | — | — | — | — | — | — | — | |
| UperNetbackbone=ViT-H12x42023.04 | 53.2 | 46.64 | 59.79 | 58.36 | 79.54 | 17.56 | 47.88 | 62.61 | — | — | — | — | — | — | — | — | — | |
| Hi-Resnet2025.03 | 52.5 | 46.7 | 58.3 | 55.9 | 80.1 | 17 | 46.7 | 62.7 | — | — | — | — | — | — | — | — | — | |
| UperNetbackbone=ViTAE-B + RVSA2023.04 | 52.44 | 46.69 | 58.14 | 57.12 | 79.66 | 16.55 | 46.46 | 62.44 | — | — | — | — | — | — | — | — | — | |
| UNetFormer2025.03 | 52.4 | 44.7 | 58.8 | 54.9 | 79.6 | 20.1 | 46 | 62.5 | — | — | — | — | — | — | — | — | — | |
| UperNetbackbone=ViT-L12x42023.04 | 52.38 | 46.17 | 60.56 | 57.26 | 76.95 | 16.05 | 47.5 | 62.17 | — | — | — | — | — | — | — | — | — | |
| MUCARatio=10%2026.01 | 51.97 | 68.69 | 58.2 | 41.82 | 65.62 | 37.09 | 35.01 | 57.38 | — | — | — | — | — | — | — | — | — | |
| UperNetbackbone=ViT-B12x12023.04 | 51.28 | 45.69 | 58.75 | 56.7 | 76.56 | 10.56 | 48.52 | 62.16 | — | — | — | — | — | — | — | — | — | |
| MUCARatio=5%2026.01 | 50.97 | 67.29 | 56.04 | 48.37 | 61.02 | 36.21 | 30.76 | 57.09 | — | — | — | — | — | — | — | — | — | |
| DWLRatio=10%2026.01 | 50.87 | 49.94 | 56.66 | 53.89 | 70.35 | 30.62 | 41.49 | 53.13 | — | — | — | — | — | — | — | — | — | |
| DC-Swin2025.03 | 50.6 | 41.3 | 54.5 | 56.2 | 78.1 | 14.5 | 47.2 | 62.4 | — | — | — | — | — | — | — | — | — | |
| AllSparkRatio=10%2026.01 | 49.86 | 67.13 | 56.16 | 40.67 | 63.58 | 32.54 | 32.03 | 56.91 | — | — | — | — | — | — | — | — | — | |
| HRNet2023.04 | 49.79 | 44.61 | 55.34 | 57.42 | 73.96 | 11.07 | 45.25 | 60.88 | — | — | — | — | — | — | — | — | — | |
| MUCARatio=1%2026.01 | 49.78 | 64.89 | 56.03 | 47.14 | 63.86 | 35.81 | 22.57 | 58.18 | — | — | — | — | — | — | — | — | — | |
| AllSparkRatio=5%2026.01 | 49.75 | 65.09 | 55.06 | 47.59 | 67.1 | 34.67 | 26.86 | 51.87 | — | — | — | — | — | — | — | — | — | |
| DWLRatio=5%2026.01 | 48.99 | 48.75 | 55 | 51.53 | 69.49 | 29.46 | 36.59 | 52.11 | — | — | — | — | — | — | — | — | — | |
| FixMatchRatio=10%2026.01 | 48.99 | 52.02 | 55.59 | 53.2 | 57.91 | 25.86 | 40.83 | 57.5 | — | — | — | — | — | — | — | — | — | |
| FactSeg2023.04 | 48.94 | 42.6 | 53.63 | 52.79 | 76.94 | 16.2 | 42.92 | 57.5 | — | — | — | — | — | — | — | — | — | |
| TransUNet2025.03 | 48.9 | 43 | 56.1 | 53.7 | 78 | 9.3 | 44.9 | 56.9 | — | — | — | — | — | — | — | — | — | |
| AllSparkRatio=1%2026.01 | 48.72 | 63.87 | 47.7 | 46.05 | 61.52 | 35.31 | 30.94 | 55.64 | — | — | — | — | — | — | — | — | — | |
| LinkNet2023.04 | 48.5 | 43.61 | 52.07 | 52.53 | 76.85 | 12.16 | 45.05 | 57.25 | — | — | — | — | — | — | — | — | — | |
| LSSTRatio=10%2026.01 | 48.32 | 50.69 | 49.5 | 52.63 | 69.85 | 27.25 | 36.24 | 52.06 | — | — | — | — | — | — | — | — | — | |
| PSPNet2023.04 | 48.31 | 44.4 | 52.13 | 53.52 | 76.5 | 9.73 | 44.07 | 57.85 | — | — | — | — | — | — | — | — | — | |
| UNet++2023.04 | 48.2 | 42.85 | 52.58 | 52.82 | 74.51 | 11.42 | 44.42 | 58.8 | — | — | — | — | — | — | — | — | — | |
| Semantic-FPN2023.04 | 48.15 | 42.93 | 51.53 | 53.43 | 74.67 | 11.21 | 44.62 | 58.68 | — | — | — | — | — | — | — | — | — | |
| FarSeg2023.04 | 48.15 | 43.09 | 51.48 | 53.85 | 76.61 | 9.78 | 43.33 | 58.9 | — | — | — | — | — | — | — | — | — | |
| LSSTRatio=5%2026.01 | 47.91 | 51.48 | 45.66 | 52.66 | 67.63 | 33.52 | 35.8 | 48.6 | — | — | — | — | — | — | — | — | — | |
| UNet2023.04 | 47.84 | 43.06 | 52.74 | 52.78 | 73.08 | 10.33 | 43.05 | 59.87 | — | — | — | — | — | — | — | — | — | |
| UniMatchRatio=10%2026.01 | 47.75 | 51.8 | 53.95 | 51.17 | 58.15 | 25.6 | 38.72 | 54.86 | — | — | — | — | — | — | — | — | — | |
| UniMatchRatio=5%2026.01 | 47.72 | 50.2 | 54.49 | 50.46 | 67.18 | 26.79 | 30.06 | 54.86 | — | — | — | — | — | — | — | — | — | |
| Mean teacherRatio=10%2026.01 | 47.68 | 50.45 | 55.75 | 43.56 | 66.15 | 35.24 | 36.96 | 45.64 | — | — | — | — | — | — | — | — | — | |
| DWLRatio=1%2026.01 | 47.67 | 48.74 | 56.79 | 51.59 | 63.42 | 22.56 | 35.2 | 55.38 | — | — | — | — | — | — | — | — | — | |
| DeepLabV3+2023.04 | 47.62 | 42.97 | 50.88 | 52.02 | 74.36 | 10.4 | 44.21 | 58.53 | — | — | — | — | — | — | — | — | — | |
| PAN2023.04 | 47.13 | 43.04 | 51.34 | 50.93 | 74.77 | 10.03 | 42.19 | 57.65 | — | — | — | — | — | — | — | — | — | |
| Unetformer2023.04 | 46.9 | 44.7 | 58.8 | 54.9 | 79.6 | 20.1 | 46 | 62.5 | — | — | — | — | — | — | — | — | — | |
| FCN8S2023.04 | 46.69 | 42.6 | 49.51 | 48.05 | 73.09 | 11.84 | 43.49 | 58.3 | — | — | — | — | — | — | — | — | — | |
| CPSRatio=10%2026.01 | 45.91 | 51.3 | 54.93 | 52.57 | 53.37 | 18.39 | 37.59 | 53.24 | — | — | — | — | — | — | — | — | — | |
| FixMatchRatio=1%2026.01 | 44.86 | 46.78 | 51.2 | 50.21 | 67.27 | 11.53 | 36.79 | 50.26 | — | — | — | — | — | — | — | — | — | |
| FixMatchRatio=5%2026.01 | 44.64 | 45.4 | 53.05 | 51.22 | 66.73 | 28.53 | 27.25 | 54.3 | — | — | — | — | — | — | — | — | — | |
| UniMatchRatio=1%2026.01 | 44.51 | 46.53 | 51.38 | 49.36 | 67.74 | 10.86 | 33.4 | 52.28 | — | — | — | — | — | — | — | — | — | |
| CutMixRatio=10%2026.01 | 44.44 | 46.73 | 49.6 | 47.36 | 59.99 | 29.06 | 37.77 | 40.6 | — | — | — | — | — | — | — | — | — | |
| Mean teacherRatio=5%2026.01 | 44.39 | 49.73 | 46.22 | 42.34 | 60.93 | 31.51 | 35.79 | 44.22 | — | — | — | — | — | — | — | — | — | |
| LSSTRatio=1%2026.01 | 42.57 | 44.73 | 41.9 | 39.9 | 62.65 | 29.27 | 31.26 | 48.29 | — | — | — | — | — | — | — | — | — | |
| CCTRatio=5%2026.01 | 42.48 | 46.8 | 44.62 | 46.8 | 60.95 | 24.83 | 29.03 | 44.3 | — | — | — | — | — | — | — | — | — | |
| CCTRatio=10%2026.01 | 42.29 | 44.07 | 45.22 | 47.65 | 57.12 | 24.41 | 32.5 | 45.07 | — | — | — | — | — | — | — | — | — | |
| CPSRatio=5%2026.01 | 42.12 | 48.9 | 49.64 | 47.97 | 60.27 | 4.67 | 36.09 | 47.32 | — | — | — | — | — | — | — | — | — | |
| GR-CoT2026.02 | 41.39 | 10.57 | 46.35 | 44.14 | 67.14 | 16.81 | 51.53 | 61.19 | 77.44 | 11.2 | 17.45 | 95.79 | 79.35 | 85 | 90.42 | 59.93 | — | |
| RSKT-Seg2026.02 | 40.71 | 0.24 | 43.18 | 44.97 | 66.45 | 30.97 | 44.48 | 54.71 | 72.77 | 0.25 | 35.28 | 93.85 | 85.18 | 79.6 | 80.71 | 57.35 | — | |
| Pi-SegBackbone=ViT-L, Type=OVRSIS, Training Dataset=DLRSD2026.04 | 39 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 61.76 | |
| Mean teacherRatio=1%2026.01 | 38.73 | 44.73 | 42.53 | 40.34 | 50.92 | 11.37 | 26.88 | 54.4 | — | — | — | — | — | — | — | — | — | |
| Pi-SegBackbone=ViT-B, Type=OVRSIS, Training Dataset=DLRSD2026.04 | 37.43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 64.47 | |
| CutMixRatio=5%2026.01 | 34.73 | 41.48 | 41.62 | 38.77 | 47.44 | 14.69 | 28.09 | 31.05 | — | — | — | — | — | — | — | — | — | |
| CAT-Seg2026.02 | 34.23 | 0.19 | 39.12 | 37.14 | 62.19 | 16.02 | 38.4 | 46.54 | 54.31 | 0.19 | 16.64 | 92.2 | 85.9 | 82.27 | 81.42 | 51.75 | — | |
| DR-SegBackbone=ViT-L, Training Dataset=DLRSD2026.04 | 34.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 56.59 | |
| GSNetBackbone=ViT-L, Training Dataset=DLRSD2026.04 | 32.52 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 60.23 | |
| RSKT-SegBackbone=ViT-B, Training Dataset=DLRSD2026.04 | 32.49 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 55.67 | |
| DR-SegBackbone=ViT-B, Training Dataset=DLRSD2026.04 | 32.38 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 56.33 | |
| OVRSBackbone=ViT-L, Training Dataset=DLRSD2026.04 | 31.53 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 59.82 | |
| Pi-SegBackbone=ViT-L, Type=OVRSIS, Training Dataset=iSAID2026.04 | 31.45 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 44.23 | |
| RSKT-SegBackbone=ViT-L, Training Dataset=DLRSD2026.04 | 31.43 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 55.23 | |
| Pi-SegBackbone=ViT-B, Type=OVRSIS, Training Dataset=iSAID2026.04 | 30.9 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 50.39 | |
| DR-SegBackbone=ViT-L, Training Dataset=iSAID2026.04 | 30.52 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 53.56 | |
| CPSRatio=1%2026.01 | 30.51 | 46.52 | 20.87 | 27.85 | 50.55 | 0.01 | 33.16 | 34.6 | — | — | — | — | — | — | — | — | — | |
| CCTRatio=1%2026.01 | 29.71 | 37.16 | 22.41 | 27.86 | 43.98 | 14.51 | 25.38 | 36.67 | — | — | — | — | — | — | — | — | — | |
| RSKT-SegBackbone=ViT-L, Training Dataset=iSAID2026.04 | 29.62 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 51.01 | |
| GSNetBackbone=ViT-B, Training Dataset=DLRSD2026.04 | 29.32 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 53.02 | |
| DR-SegBackbone=ViT-B, Training Dataset=iSAID2026.04 | 28.97 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 52.74 | |
| OVRSBackbone=ViT-B, Training Dataset=DLRSD2026.04 | 28.67 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 52.1 | |
| Cat-SegBackbone=ViT-L, Training Dataset=DLRSD2026.04 | 28.64 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 38.73 | |
| RSKT-SegBackbone=ViT-B, Training Dataset=iSAID2026.04 | 28.07 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 46.58 | |
| OVRSBackbone=ViT-L, Training Dataset=iSAID2026.04 | 27.98 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 49.01 | |
| GSNetBackbone=ViT-L, Training Dataset=iSAID2026.04 | 27.21 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 49.53 | |
| GSNetBackbone=ViT-B, Training Dataset=iSAID2026.04 | 26.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 42.84 | |
| Cat-SegBackbone=ViT-B, Training Dataset=DLRSD2026.04 | 25.45 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 50.32 | |
| SANBackbone=ViT-L, Training Dataset=DLRSD2026.04 | 25.33 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 37.54 | |
| OVRSBackbone=ViT-B, Training Dataset=iSAID2026.04 | 25.3 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 42.32 | |
| Cat-SegBackbone=ViT-L, Training Dataset=iSAID2026.04 | 25.11 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 48.25 | |
| SEDBackbone=ConvNeXt-L, Training Dataset=DLRSD2026.04 | 24.55 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 36.83 | |
| Cat-SegBackbone=ViT-B, Training Dataset=iSAID2026.04 | 23.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 41.55 | |
| SEDBackbone=ConvNeXt-L, Training Dataset=iSAID2026.04 | 23.24 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 45.13 | |
| SCANBackbone=ViT-L, Training Dataset=DLRSD2026.04 | 23.17 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 35.36 | |
| SANBackbone=ViT-B, Training Dataset=DLRSD2026.04 | 23.15 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 48.26 | |
| SANBackbone=ViT-L, Training Dataset=iSAID2026.04 | 22.33 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 44.22 | |
| SEDBackbone=ConvNeXt-B, Training Dataset=DLRSD2026.04 | 21.32 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 45.17 | |
| SEDBackbone=ConvNeXt-B, Training Dataset=iSAID2026.04 | 20.1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 42.3 | |
| SCANBackbone=ViT-L, Training Dataset=iSAID2026.04 | 18.5 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 38.2 | |
| SANBackbone=ViT-B, Training Dataset=iSAID2026.04 | 18.45 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 40.25 | |
| SCANBackbone=ViT-B, Training Dataset=DLRSD2026.04 | 18.23 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 40.12 | |
| SCANBackbone=ViT-B, Type=OVS, Training Dataset=DLRSD2026.04 | 18.23 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 40.12 | |
| CutMixRatio=1%2026.01 | 16.52 | 36.04 | 24.69 | 10.03 | 24.6 | 3.43 | 6.67 | 10.19 | — | — | — | — | — | — | — | — | — | |
| SCANBackbone=ViT-B, Training Dataset=iSAID2026.04 | 12.56 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 32.1 |