UPerNet
| family | model | params (m) | pretrain | head | train | GFLOPs | mIoUms |
|---|---|---|---|---|---|---|---|
| Swin | Swin-B | 88.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1188.0 | 49.7 |
| CSWin | CSWin-T | 23.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 959.0 | 50.7 |
| TransNeXt | TransNeXt-T | 28.2 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 978.0 | 51.7 |
| InternImage | InternImage-XL | 335.0 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 640 | 3142.0 | 55.3 |
| FocalNet | FocalNet-S-SRF | 50.3 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1035.0 | 50.1 |
| RepLKNet | RepLKNet-XL | 335.0 | MegData73M : Sup. : 15 | UPerNet | ADE20K (train) : 128 : 640 | 3431.0 | 56.0 |
| Swin | Swin-S | 50.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1038.0 | 49.5 |
| CAFormer | CAFormer-S36 | 39.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1197.0 | 50.8 |
| CAFormer | CAFormer-M36 | 56.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1346.0 | 51.7 |
| Swin | Swin-T | 29.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 945.0 | 45.8 |
| FocalNet | FocalNet-T-SRF | 28.4 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 944.0 | 47.2 |
| VMamba | VMamba-T | 30.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 949.0 | 48.8 |
| DAT++ | DAT-S++ | 53.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1098.0 | 51.2 |
| RepLKNet | RepLKNet-31B | 79.0 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 512 | 1829.0 | 52.3 |
| InternImage | InternImage-T | 30.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 944.0 | 48.1 |
| ConvNeXt | ConvNeXt-B | 89.0 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 640 | 1828.0 | 53.1 |
| VMamba | VMamba-B | 89.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1170.0 | 51.6 |
| ConvNeXt | ConvNeXt-B | 89.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1170.0 | 49.9 |
| UniRepLKNet | UniRepLKNet-S | 55.6 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1036.0 | 51.0 |
| RepLKNet | RepLKNet-31L | 172.0 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 512 | 2404.0 | 52.7 |
| FocalNet | FocalNet-S-LRF | 50.3 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1044.0 | 50.1 |
| ConvNeXt V2 | ConvNeXt V2-L | 198.0 | IN-1k : FCMAE : 1600 | UPerNet | ADE20K (train) : 128 : 512 | 1573.0 | 53.7 |
| LocalVMamba | LocalVMamba-S | 50.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1095.0 | 51.0 |
| TransNeXt | TransNeXt-S | 49.7 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1089.0 | 52.8 |
| CSWin | CSWin-B | 78.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1222.0 | 52.2 |
| DeiT III | ViT-L (DeiT III) | 304.4 | IN-1k : Sup. : 800 | UPerNet | ADE20K (train) : 128 : 512 | 2231.0 | 52.0 |
| LocalVMamba | LocalVMamba-T | 26.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 970.0 | 49.1 |
| Swin | Swin-L | 197.0 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 640 | 3230.0 | 53.5 |
| ConvNeXt | ConvNeXt-T | 29.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 939.0 | 46.7 |
| ConvFormer | ConvFormer-M36 | 57.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1113.0 | 51.3 |
| UniRepLKNet | UniRepLKNet-T | 31.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 946.0 | 49.1 |
| RepLKNet | RepLKNet-31B | 79.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1170.0 | 50.6 |
| DAT++ | DAT-B++ | 93.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1268.0 | 51.5 |
| MambaOut | MambaOut-T | 26.5 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 938.0 | 48.6 |
| MambaOut | MambaOut-S | 48.5 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1032.0 | 50.6 |
| CSWin | CSWin-B | 78.0 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 640 | 1941.0 | 52.6 |
| UniRepLKNet | UniRepLKNet-S | 55.6 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 640 | 1618.0 | 52.7 |
| ConvNeXt | ConvNeXt-S | 50.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1027.0 | 49.6 |
| ConvNeXt V2 | ConvNeXt V2-H | 660.0 | IN-1k : FCMAE : 1600 | UPerNet | ADE20K (train) : 128 : 512 | 3272.0 | 55.0 |
| DAMamba | DAMamba-T | 26.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 937.0 | 51.2 |
| DeiT III | ViT-S (DeiT III) | 22.0 | IN-1k : Sup. : 800 | UPerNet | ADE20K (train) : 128 : 512 | 588.0 | 46.8 |
| EfficientVMamba | EfficientVMamba-T | 6.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 230.0 | 39.3 |
| DeiT III | ViT-B (DeiT III) | 86.6 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 512 | 1283.0 | 52.8 |
| UniRepLKNet | UniRepLKNet-XL | 386.4 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 640 | 3420.0 | 55.6 |
| DeiT III | ViT-L (DeiT III) | 304.4 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 512 | 2231.0 | 54.7 |
| LocalVim | LocalVim-T | 8.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 181.0 | 44.4 |
| FocalNet | FocalNet-B-LRF | 88.7 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1192.0 | 51.4 |
| EfficientVMamba | EfficientVMamba-S | 11.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 505.0 | 42.1 |
| LocalVim | LocalVim-S | 28.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 297.0 | 47.5 |
| InternImage | InternImage-B | 97.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1185.0 | 51.3 |
| DAT++ | DAT-T++ | 24.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 969.0 | 50.3 |
| InternImage | InternImage-L | 223.0 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 640 | 2526.0 | 54.1 |
| ConvNeXt | ConvNeXt-XL | 350.0 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 640 | 3335.0 | 54.0 |
| FocalNet | FocalNet-B-SRF | 88.1 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1180.0 | 51.1 |
| ConvFormer | ConvFormer-S18 | 27.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 925.0 | 48.6 |
| DAMamba | DAMamba-S | 45.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1050.0 | 52.0 |
| EfficientVMamba | EfficientVMamba-B | 33.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 930.0 | 47.3 |
| MambaOut | MambaOut-B | 84.8 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1178.0 | 51.0 |
| VSSD | VSSD-M | 14.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 893.0 | 46.0 |
| Swin | Swin-B | 88.0 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 640 | 1841.0 | 51.7 |
| InternImage | InternImage-S | 50.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1017.0 | 50.9 |
| ConvNeXt | ConvNeXt-L | 198.0 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 640 | 2458.0 | 53.7 |
| VSSD | VSSD-T | 24.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 941.0 | 48.7 |
| UniRepLKNet | UniRepLKNet-B | 97.9 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 640 | 1850.0 | 53.9 |
| CSWin | CSWin-L | 173.0 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 640 | 2745.0 | 55.7 |
| DeiT III | ViT-B (DeiT III) | 86.6 | IN-1k : Sup. : 800 | UPerNet | ADE20K (train) : 128 : 512 | 1283.0 | 50.2 |
| TransNeXt | TransNeXt-B | 89.7 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1268.0 | 53.7 |
| ConvFormer | ConvFormer-S36 | 40.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1003.0 | 50.7 |
| VMamba | VMamba-S | 50.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1028.0 | 51.2 |
| UniRepLKNet | UniRepLKNet-L | 218.3 | IN-22k : Sup. : 90 | UPerNet | ADE20K (train) : 128 : 640 | 2507.0 | 55.1 |
| CSWin | CSWin-S | 35.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1027.0 | 51.5 |
| CAFormer | CAFormer-S18 | 26.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1024.0 | 48.9 |
| ConvNeXt V2 | ConvNeXt V2-B | 89.0 | IN-1k : FCMAE : 1600 | UPerNet | ADE20K (train) : 128 : 512 | 1170.0 | 52.1 |
| DAMamba | DAMamba-B | 86.0 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 1178.0 | 52.3 |
| FocalNet | FocalNet-T-LRF | 28.6 | IN-1k : Sup. : 300 | UPerNet | ADE20K (train) : 128 : 512 | 949.0 | 47.8 |
ADE20K (val)
| family | model | pretrain | train | gflops | mIoUms | pAccms | mAccms | mIoUss | pAccss | mAccss |
|---|---|---|---|---|---|---|---|---|---|---|
| TransNeXt | TransNeXt-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 978.0 | 51.7 | — | — | 51.1 | — | — |
| TransNeXt | TransNeXt-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1089.0 | 52.8 | — | — | 52.5 | — | — |
| TransNeXt | TransNeXt-B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1268.0 | 53.7 | — | — | 53.0 | — | — |
| ConvNeXt | ConvNeXt-L | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 2458.0 | 53.7 | — | — | 53.2 | — | — |
| ConvNeXt | ConvNeXt-B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1170.0 | 49.9 | — | — | 49.1 | — | — |
| ConvNeXt | ConvNeXt-B | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 1828.0 | 53.1 | — | — | 52.6 | — | — |
| ConvNeXt | ConvNeXt-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1027.0 | 49.6 | — | — | 48.7 | — | — |
| ConvNeXt | ConvNeXt-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 939.0 | 46.7 | — | — | 46.0 | — | — |
| ConvNeXt | ConvNeXt-XL | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 3335.0 | 54.0 | — | — | 53.6 | — | — |
| Swin | Swin-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 945.0 | 45.8 | — | — | 44.5 | — | — |
| Swin | Swin-B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1188.0 | 49.7 | — | — | 48.1 | — | — |
| Swin | Swin-B | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 1841.0 | 51.7 | — | — | 50.0 | — | — |
| Swin | Swin-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1038.0 | 49.5 | — | — | 47.6 | — | — |
| Swin | Swin-L | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 3230.0 | 53.5 | — | — | 52.1 | — | — |
| DeiT III | ViT-S (DeiT III) | IN-1k : Sup. : 800 | ADE20K (train) : 128 : 512 | 588.0 | 46.8 | — | — | 45.6 | — | — |
| DeiT III | ViT-B (DeiT III) | IN-1k : Sup. : 800 | ADE20K (train) : 128 : 512 | 1283.0 | 50.2 | — | — | 49.3 | — | — |
| DeiT III | ViT-B (DeiT III) | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 512 | 1283.0 | 52.8 | — | — | 51.8 | — | — |
| DeiT III | ViT-L (DeiT III) | IN-1k : Sup. : 800 | ADE20K (train) : 128 : 512 | 2231.0 | 52.0 | — | — | 51.5 | — | — |
| DeiT III | ViT-L (DeiT III) | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 512 | 2231.0 | 54.7 | — | — | 53.8 | — | — |
| ConvNeXt V2 | ConvNeXt V2-H | IN-1k : FCMAE : 1600 | ADE20K (train) : 128 : 512 | 3272.0 | 55.0 | — | — | — | — | — |
| ConvNeXt V2 | ConvNeXt V2-L | IN-1k : FCMAE : 1600 | ADE20K (train) : 128 : 512 | 1573.0 | 53.7 | — | — | — | — | — |
| ConvNeXt V2 | ConvNeXt V2-B | IN-1k : FCMAE : 1600 | ADE20K (train) : 128 : 512 | 1170.0 | 52.1 | — | — | — | — | — |
| InternImage | InternImage-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 944.0 | 48.1 | — | — | 47.9 | — | — |
| InternImage | InternImage-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1017.0 | 50.9 | — | — | 50.1 | — | — |
| InternImage | InternImage-B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1185.0 | 51.3 | — | — | 50.8 | — | — |
| InternImage | InternImage-L | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 2526.0 | 54.1 | — | — | 53.9 | — | — |
| InternImage | InternImage-XL | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 3142.0 | 55.3 | — | — | 55.0 | — | — |
| FocalNet | FocalNet-T-LRF | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 949.0 | 47.8 | — | — | 46.8 | — | — |
| FocalNet | FocalNet-T-SRF | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 944.0 | 47.2 | — | — | 46.5 | — | — |
| FocalNet | FocalNet-S-SRF | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1035.0 | 50.1 | — | — | 49.3 | — | — |
| FocalNet | FocalNet-S-LRF | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1044.0 | 50.1 | — | — | 49.1 | — | — |
| FocalNet | FocalNet-B-LRF | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1192.0 | 51.4 | — | — | 50.5 | — | — |
| FocalNet | FocalNet-B-SRF | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1180.0 | 51.1 | — | — | 50.2 | — | — |
| CSWin | CSWin-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 959.0 | 50.7 | — | — | 49.3 | — | — |
| CSWin | CSWin-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1027.0 | 51.5 | — | — | 50.4 | — | — |
| CSWin | CSWin-B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1222.0 | 52.2 | — | — | 51.1 | — | — |
| CSWin | CSWin-B | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 1941.0 | 52.6 | — | — | 51.8 | — | — |
| CSWin | CSWin-L | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 2745.0 | 55.7 | — | — | 54.0 | — | — |
| CAFormer | CAFormer-S18 | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1024.0 | 48.9 | — | — | — | — | — |
| CAFormer | CAFormer-S36 | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1197.0 | 50.8 | — | — | — | — | — |
| CAFormer | CAFormer-M36 | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1346.0 | 51.7 | — | — | — | — | — |
| ConvFormer | ConvFormer-S18 | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 925.0 | 48.6 | — | — | — | — | — |
| ConvFormer | ConvFormer-S36 | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1003.0 | 50.7 | — | — | — | — | — |
| ConvFormer | ConvFormer-M36 | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1113.0 | 51.3 | — | — | — | — | — |
| MogaNet | MogaNet-XT | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 856.0 | — | — | — | 42.2 | — | — |
| MogaNet | MogaNet-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 862.0 | — | — | — | 43.7 | — | — |
| MogaNet | MogaNet-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 946.0 | — | — | — | 49.2 | — | — |
| MogaNet | MogaNet-B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1050.0 | — | — | — | 50.1 | — | — |
| MogaNet | MogaNet-L | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1176.0 | — | — | — | 50.9 | — | — |
| MogaNet | MogaNet-XL | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 2451.0 | — | — | — | 54.0 | — | — |
| VMamba | VMamba-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 949.0 | 48.8 | — | — | 47.9 | — | — |
| VMamba | VMamba-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1028.0 | 51.2 | — | — | 50.6 | — | — |
| VMamba | VMamba-B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1170.0 | 51.6 | — | — | 51.0 | — | — |
| UniRepLKNet | UniRepLKNet-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 946.0 | 49.1 | — | — | 48.6 | — | — |
| UniRepLKNet | UniRepLKNet-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1036.0 | 51.0 | — | — | 50.5 | — | — |
| UniRepLKNet | UniRepLKNet-S | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 1618.0 | 52.7 | — | — | 51.9 | — | — |
| UniRepLKNet | UniRepLKNet-B | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 1850.0 | 53.9 | — | — | 53.5 | — | — |
| UniRepLKNet | UniRepLKNet-L | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 2507.0 | 55.1 | — | — | 54.5 | — | — |
| UniRepLKNet | UniRepLKNet-XL | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 3420.0 | 55.6 | — | — | 55.2 | — | — |
| BiFormer | BiFormer-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | None | 50.8 | — | — | 49.8 | — | — |
| SLaK | SLaK-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 936.0 | — | — | — | 47.6 | — | — |
| SLaK | SLaK-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1028.0 | — | — | — | 49.4 | — | — |
| SLaK | SLaK-B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1172.0 | — | — | — | 50.2 | — | — |
| RepLKNet | RepLKNet-31B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1170.0 | 50.6 | — | — | 49.9 | — | — |
| RepLKNet | RepLKNet-31B | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 512 | 1829.0 | 52.3 | — | — | 51.5 | — | — |
| RepLKNet | RepLKNet-31L | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 512 | 2404.0 | 52.7 | — | — | 52.4 | — | — |
| RepLKNet | RepLKNet-XL | MegData73M : Sup. : 15 | ADE20K (train) : 128 : 640 | 3431.0 | 56.0 | — | — | 55.2 | — | — |
| BiFormer | BiFormer-B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | None | 51.7 | — | — | 51.0 | — | — |
| MambaOut | MambaOut-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 938.0 | 48.6 | — | — | 47.4 | — | — |
| MambaOut | MambaOut-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1032.0 | 50.6 | — | — | 49.5 | — | — |
| MambaOut | MambaOut-B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1178.0 | 51.0 | — | — | 49.6 | — | — |
| GroupMamba | GroupMamba-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | None | 49.2 | — | — | 48.6 | — | — |
| Vim | Vim-Ti | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | None | — | — | — | 41.0 | — | — |
| Vim | Vim-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | None | — | — | — | 44.9 | — | — |
| PlainMamba | PlainMamba-L1 | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 174.0 | — | — | — | 44.1 | — | — |
| PlainMamba | PlainMamba-L2 | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 285.0 | — | — | — | 46.8 | — | — |
| PlainMamba | PlainMamba-L3 | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 419.0 | — | — | — | 49.1 | — | — |
| LocalVim | LocalVim-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 181.0 | 44.4 | — | — | 43.4 | — | — |
| LocalVim | LocalVim-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 297.0 | 47.5 | — | — | 46.4 | — | — |
| LocalVMamba | LocalVMamba-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 970.0 | 49.1 | — | — | 47.9 | — | — |
| LocalVMamba | LocalVMamba-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1095.0 | 51.0 | — | — | 50.0 | — | — |
| EfficientVMamba | EfficientVMamba-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 230.0 | 39.3 | — | — | 38.9 | — | — |
| EfficientVMamba | EfficientVMamba-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 505.0 | 42.1 | — | — | 41.5 | — | — |
| EfficientVMamba | EfficientVMamba-B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 930.0 | 47.3 | — | — | 46.5 | — | — |
| DAMamba | DAMamba-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 937.0 | 51.2 | — | — | 50.3 | — | — |
| DAMamba | DAMamba-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1050.0 | 52.0 | — | — | 51.2 | — | — |
| DAMamba | DAMamba-B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1178.0 | 52.3 | — | — | 51.9 | — | — |
| VSSD | VSSD-M | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 893.0 | 46.0 | — | — | 45.6 | — | — |
| VSSD | VSSD-T | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 941.0 | 48.7 | — | — | 47.9 | — | — |
| RMT | RMT-S | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 937.0 | — | — | — | 49.8 | — | — |
| RMT | RMT-B | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1051.0 | — | — | — | 52.0 | — | — |
| RMT | RMT-L | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1241.0 | — | — | — | 52.8 | — | — |
| DAT++ | DAT-T++ | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 969.0 | 50.3 | — | — | 49.4 | — | — |
| DAT++ | DAT-S++ | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1098.0 | 51.2 | — | — | 50.5 | — | — |
| DAT++ | DAT-B++ | IN-1k : Sup. : 300 | ADE20K (train) : 128 : 512 | 1268.0 | 51.5 | — | — | 51.0 | — | — |
ADE20K (test)
| family | model | pretrain | train | gflops | mIoUms | pAccms | mAccms | mIoUss | pAccss | mAccss |
|---|---|---|---|---|---|---|---|---|---|---|
| Swin | Swin-L | IN-22k : Sup. : 90 | ADE20K (train) : 128 : 640 | 3230.0 | 62.8 | — | — | — | — | — |
Cityscapes (val)
| family | model | pretrain | train | gflops | mIoUms | pAccms | mAccms | mIoUss | pAccss | mAccss |
|---|---|---|---|---|---|---|---|---|---|---|
| RepLKNet | RepLKNet-31B | IN-1k : Sup. : 300 | Cityscapes (train) : 128 : 512 | 2315.0 | 83.5 | — | — | 83.1 | — | — |