Video Semantic Segmentation on VSPW
63.6mIoUVideo-kMax
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Video-kMaxBackbone=ConvNeXtL, Joint Training=false, Universal=false2024.02 | 63.6 | 91.8 | — | — | |
| TubeFormerBackbone=A-R50x64, Joint Training=false, Universal=false2024.02 | 63.2 | 92.1 | — | — | |
| UniVSBackbone=SwinL, Joint Training=true, Universal=true2024.02 | 59.8 | 92.3 | — | — | |
| Tube-LinkBackbone=SwinL, Joint Training=false, Universal=false2024.02 | 59.7 | 90.3 | — | — | |
| UniVSBackbone=SwinB, Joint Training=true, Universal=true2024.02 | 59.4 | 90.4 | — | — | |
| RS-SSMBackbone=Swin-S, GFLOPs=110.3, Params(M)=55.9, FPS=24.2, Input Resolution=480 × 8532026.03 | 52.2 | — | — | — | |
| RS-SSMBackbone=MiT-B5, GFLOPs=128.8, Params(M)=88.4, FPS=20.2, Input Resolution=480 × 8532026.03 | 51.6 | — | — | — | |
| UniVSBackbone=SwinT, Joint Training=true, Universal=true2024.02 | 51.3 | 89.4 | — | — | |
| TV3SBackbone=Swin-S, GFLOPs=94.1, Params(M)=53.1, FPS=19.5, Input Resolution=480 × 8532026.03 | 50.6 | — | — | — | |
| TV3SBackbone=MiT-B5, GFLOPs=137, Params(M)=85.6, FPS=14, Resolution=480 x 8532025.03 | 50.4 | 91.9 | 89.1 | — | |
| CFFM++Backbone=MiT-B5, GFLOPs=444.3, Params(M)=87.5, FPS=10.4, Input Resolution=480 × 8532026.03 | 50.1 | — | — | — | |
| MRCFABackbone=MiT-B5, GFLOPs=373, Params(M)=84.5, FPS=5, Resolution=480 x 8532025.03 | 49.9 | 90.9 | 87.4 | — | |
| MRCFABackbone=MiT-B5, GFLOPs=373.0, Params(M)=84.5, FPS=5.0, Input Resolution=480 × 8532026.03 | 49.9 | — | — | — | |
| TV3SBackbone=MiT-B5, GFLOPs=137.0, Params(M)=85.6, FPS=14.0, Input Resolution=480 × 8532026.03 | 49.8 | — | — | — | |
| CFFMBackbone=MiTB52024.02 | 49.3 | 90.8 | — | — | |
| CFFMBackbone=MiT-B5, GFLOPs=413.5, Params(M)=85.5, FPS=4.5, Resolution=480 x 8532025.03 | 49.3 | 90.8 | 87.1 | — | |
| SegformerBackbone=MiT-B5, GFLOPs=185, Params(M)=82.1, FPS=9.4, Resolution=480 x 8532025.03 | 48.9 | 87.8 | 83.7 | — | |
| SegformerBackbone=MiT-B5, GFLOPs=185.0, Params(M)=82.1, FPS=9.4, Input Resolution=480 × 8532026.03 | 48.9 | — | — | — | |
| UniVSBackbone=ResNet50, Joint Training=true, Universal=true2024.02 | 48.2 | 88.5 | — | — | |
| RS-SSMBackbone=MiT-B2, GFLOPs=60.7, Params(M)=31.2, FPS=30.9, Input Resolution=480 × 8532026.03 | 46.8 | — | — | — | |
| TV3SBackbone=MiT-B2, GFLOPs=53.9, Params(M)=28.3, FPS=21.9, Input Resolution=480 × 8532026.03 | 46.3 | — | — | — | |
| RS-SSMBackbone=Swin-T, GFLOPs=73.5, Params(M)=34.6, FPS=26.7, Input Resolution=480 × 8532026.03 | 46.1 | — | — | — | |
| CFFM++Backbone=MiT-B2, GFLOPs=172.6, Params(M)=28.5, FPS=21.5, Input Resolution=480 × 8532026.03 | 45.5 | — | — | — | |
| MRCFABackbone=MiT-B2, GFLOPs=127.9, Params(M)=27.3, FPS=10.7, Input Resolution=480 × 8532026.03 | 45.3 | — | — | — | |
| TV3SBackbone=Swin-T, GFLOPs=57.3, Params(M)=31.7, FPS=22.9, Input Resolution=480 × 8532026.03 | 44.9 | — | — | — | |
| Video-kMaxBackbone=ResNet50, Joint Training=false, Universal=false2024.02 | 44.3 | 86 | — | — | |
| SegformerBackbone=MiT-B2, GFLOPs=100.8, Params(M)=24.8, FPS=16.2, Input Resolution=480 × 8532026.03 | 43.9 | — | — | — | |
| Tube-LinkBackbone=ResNet50, Joint Training=false, Universal=false2024.02 | 42.3 | 86.8 | — | — | |
| Mask2FormerBackbone=Swin-S, GFLOPs=152.2, Params(M)=68.9, FPS=14.5, Input Resolution=480 × 8532026.03 | 42.1 | — | — | — | |
| RS-SSMBackbone=MiT-B1, GFLOPs=48.1, Params(M)=20.2, FPS=37.3, Input Resolution=480 × 8532026.03 | 41.7 | — | — | — | |
| Mask2FormerBackbone=Swin-T, GFLOPs=114.4, Params(M)=47.4, FPS=17.1, Input Resolution=480 × 8532026.03 | 41.2 | — | — | — | |
| MPVSSBackbone=Swin-S, GFLOPs=47.3, Params(M)=108.0, FPS=30.6, Input Resolution=480 × 8532026.03 | 40.4 | — | — | — | |
| TV3SBackbone=MiT-B1, GFLOPs=36.9, Params(M)=17.3, FPS=24.7, Input Resolution=480 × 8532026.03 | 40 | — | — | — | |
| CFFM++Backbone=MiT-B1, GFLOPs=114.3, Params(M)=16.5, FPS=27.6, Input Resolution=480 × 8532026.03 | 39.9 | — | — | — | |
| MPVSSBackbone=Swin-T, GFLOPs=39.7, Params(M)=114.0, FPS=32.8, Input Resolution=480 × 8532026.03 | 39.9 | — | — | — | |
| Mask2FormerBackbone=R101, GFLOPs=141.3, Params(M)=63, FPS=16.9, Resolution=480 x 8532025.03 | 39.3 | 82.5 | 77.6 | — | |
| Mask2FormerBackbone=R101, GFLOPs=141.3, Params(M)=63.0, FPS=16.9, Input Resolution=480 × 8532026.03 | 39.3 | — | — | — | |
| MRCFABackbone=MiT-B1, GFLOPs=77.5, Params(M)=16.2, FPS=40.1, Input Resolution=480 × 8532026.03 | 38.9 | — | — | — | |
| MPVSSBackbone=R101, GFLOPs=45.1, Params(M)=103.1, FPS=32.3, Resolution=480 x 8532025.03 | 38.8 | 84.8 | 79.6 | — | |
| MPVSSBackbone=R101, GFLOPs=45.1, Params(M)=103.1, FPS=32.3, Input Resolution=480 × 8532026.03 | 38.8 | — | — | — | |
| Mask2FormerBackbone=R50, GFLOPs=110.6, Params(M)=44, FPS=19.4, Resolution=480 x 8532025.03 | 38.5 | 81.3 | 76.4 | — | |
| Mask2FormerBackbone=R50, GFLOPs=110.6, Params(M)=44.0, FPS=19.4, Input Resolution=480 × 8532026.03 | 38.5 | — | — | — | |
| T-REN2026.04 | 38.3 | — | — | 254.5 | |
| TCBBackbone=R1012024.02 | 37.8 | 87.8 | — | — | |
| TCBBackbone=R101, GFLOPs=1692, Resolution=480 x 8532025.03 | 37.8 | 87.9 | 84 | — | |
| MPVSSBackbone=R50, GFLOPs=38.9, Params(M)=84.1, FPS=33.9, Resolution=480 x 8532025.03 | 37.5 | 84.1 | 77.2 | — | |
| ETCBackbone=OCRNet, GFLOPs=361.7, Resolution=480 x 8532025.03 | 37.5 | 84.1 | 79.1 | — | |
| MPVSSBackbone=R50, GFLOPs=38.9, Params(M)=84.1, FPS=33.9, Input Resolution=480 × 8532026.03 | 37.5 | — | — | — | |
| OCRNetBackbone=R101, GFLOPs=361.7, Params(M)=58.1, FPS=14.3, Resolution=480 x 8532025.03 | 36.7 | 84 | 79 | — | |
| UperNetBackbone=R101, GFLOPs=403.6, Params(M)=83.2, FPS=16, Resolution=480 x 8532025.03 | 36.5 | 82.6 | 76.1 | — | |
| PSPNetBackbone=R101, GFLOPs=401.8, Params(M)=70.5, FPS=13.8, Resolution=480 x 8532025.03 | 36.5 | 84.2 | 79.6 | — | |
| SegformerBackbone=MiT-B1, GFLOPs=26.6, Params(M)=13.8, FPS=58.7, Input Resolution=480 × 8532026.03 | 36.5 | — | — | — | |
| DeepLabv3+Backbone=R101, GFLOPs=379, Params(M)=62.7, FPS=9.2, Resolution=480 x 8532025.03 | 34.7 | 83.2 | 78.2 | — | |
| DINOv3 dino.txtrepresentation=dino.txt2026.04 | 20.7 | — | — | 1 | |
| REN2026.04 | 18.5 | — | — | 22.9 |