Video Semantic Segmentation on VSPW (test)
56.1mIoUMask2Former
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Mask2FormerBackbone=Swin-L, GFLOPs=402.7, Params(M)=215.1, FPS=8.412023.10 | 56.1 | 70.8 | 87.6 | 84.1 | |
| Mask2FormerBackbone=Swin-B, GFLOPs=223.5, Params(M)=107.1, FPS=11.452023.10 | 54.1 | 70.3 | 86.6 | 82.9 | |
| MPVSSBackbone=Swin-L, GFLOPs=97.3, Params(M)=255.4, FPS=23.222023.10 | 53.9 | 69.1 | 89.6 | 85.8 | |
| MPVSSBackbone=Swin-B, GFLOPs=61.5, Params(M)=147, FPS=27.382023.10 | 52.6 | 68.4 | 89.5 | 85.9 | |
| MRCFABackbone=MiT-B5, GFLOPs=373, Params(M)=84.5, FPS=5.022023.10 | 49.9 | 66 | 90.9 | 87.4 | |
| CFFM-VSSBackbone=MiT-B5, GFLOPs=413.5, Params(M)=85.5, FPS=4.582023.10 | 49.3 | 65.8 | 90.8 | 87.1 | |
| SegformerBackbone=MiT-B5, GFLOPs=185, Params(M)=82.1, FPS=9.482023.10 | 48.9 | 65.1 | 87.8 | 83.7 | |
| MRCFABackbone=MiT-B2, GFLOPs=127.9, Params(M)=27.3, FPS=10.72023.10 | 45.3 | 64.7 | 90.3 | 86.2 | |
| CFFM-VSSBackbone=MiT-B2, GFLOPs=143.2, Params(M)=26.5, FPS=10.082023.10 | 44.9 | 64.9 | 89.8 | 85.8 | |
| SegformerBackbone=MiT-B2, GFLOPs=100.8, Params(M)=24.8, FPS=16.162023.10 | 43.9 | 63.7 | 86 | 81.2 | |
| Mask2FormerBackbone=Swin-S, GFLOPs=152.2, Params(M)=68.9, FPS=14.522023.10 | 42.1 | 63.1 | 84.7 | 79.3 | |
| Mask2FormerBackbone=Swin-T, GFLOPs=114.4, Params(M)=47.4, FPS=17.132023.10 | 41.2 | 62.6 | 84.5 | 80 | |
| MPVSSBackbone=Swin-S, GFLOPs=47.3, Params(M)=108, FPS=30.612023.10 | 40.4 | 62 | 86 | 80.7 | |
| MPVSSBackbone=Swin-T, GFLOPs=39.7, Params(M)=114, FPS=32.862023.10 | 39.9 | 62 | 85.9 | 80.4 | |
| Mask2FormerBackbone=R101, GFLOPs=141.3, Params(M)=63, FPS=16.92023.10 | 39.3 | 60.1 | 82.5 | 77.6 | |
| MPVSSBackbone=R101, GFLOPs=45.1, Params(M)=103.1, FPS=32.382023.10 | 38.8 | 59 | 84.8 | 79.6 | |
| Mask2FormerBackbone=R50, GFLOPs=110.6, Params(M)=44, FPS=19.42023.10 | 38.5 | 60.2 | 81.3 | 76.4 | |
| TCBBackbone=R101, GFLOPs=16922023.10 | 37.8 | 59.5 | 87.9 | 84 | |
| ETCBackbone=OCRNet, GFLOPs=361.72023.10 | 37.5 | 59.1 | 84.1 | 79.1 | |
| NetWarpBackbone=OCRNet, GFLOPs=12072023.10 | 37.5 | 58.9 | 84 | 79 | |
| MPVSSBackbone=R50, GFLOPs=38.9, Params(M)=84.1, FPS=33.932023.10 | 37.5 | 59 | 84.1 | 77.2 | |
| OCRNetBackbone=R101, GFLOPs=361.7, Params(M)=58.1, FPS=14.392023.10 | 36.7 | 59.2 | 84 | 79 | |
| UperNetBackbone=R101, GFLOPs=403.6, Params(M)=83.2, FPS=16.052023.10 | 36.5 | 58.6 | 82.6 | 76.1 | |
| PSPNetBackbone=R101, GFLOPs=401.8, Params(M)=70.5, FPS=13.842023.10 | 36.5 | 58.1 | 84.2 | 79.6 | |
| DeepLab3+Backbone=R101, GFLOPs=379, Params(M)=62.7, FPS=9.252023.10 | 34.7 | 58.8 | 83.2 | 78.2 |