Semantic Segmentation on MaSS 13K 1,500 (test)
88.21mIoUMaSSFormer
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MaSSFormerBackbone=R50, Param=37.42M, FLOPs=2036G, Input Resolution=4096 x 40962025.03 | 88.21 | 48.39 | 55.93 | |
| SegNeXtBackbone=MSCAN-B, Param=27.57M, FLOPs=1536G, Input Resolution=4096 x 40962025.03 | 88.11 | 39.45 | 45.96 | |
| Mask2FormerBackbone=R50, Param=44.01M, FLOPs=3123G, Input Resolution=4096 x 40962025.03 | 88 | 46.13 | 53.3 | |
| SeaFormer-LParam=13.95M, FLOPs=303G, Input Resolution=4096 x 40962025.03 | 87.36 | 38.28 | 44.89 | |
| MPFormerBackbone=R50, Param=43.9M, FLOPs=4155G, Input Resolution=4096 x 40962025.03 | 87.18 | 47.17 | 54.86 | |
| FeedFormerBackbone=lvt, Param=4.65M, FLOPs=300G, Input Resolution=4096 x 40962025.03 | 86.56 | 41.07 | 47.89 | |
| MaSSFormer-LiteBackbone=R18, Param=15.07M, FLOPs=771G, Input Resolution=4096 x 40962025.03 | 86.13 | 43.28 | 50.86 | |
| DeepLabv3+Backbone=R50, Param=41.22M, FLOPs=8008G, Input Resolution=4096 x 40962025.03 | 85.14 | 38.65 | 46.78 | |
| STDC2Param=12.30M, FLOPs=564G, Input Resolution=4096 x 40962025.03 | 83.76 | 27.72 | 33.32 | |
| PEMBackbone=R50, Param=35.5M, FLOPs=1859G, Input Resolution=4096 x 40962025.03 | 83.38 | 39.99 | 46.44 | |
| MaskFormerBackbone=R50, Param=41.31M, FLOPs=2396G, Input Resolution=4096 x 40962025.03 | 83.22 | 37.9 | 43.93 | |
| OCRNetBackbone=R50, Param=36.52M, FLOPs=7352G, Input Resolution=4096 x 40962025.03 | 83.02 | 31.33 | 37.31 | |
| UperNetBackbone=R50, Param=64.04M, FLOPs=11373G, Input Resolution=4096 x 40962025.03 | 81.98 | 35.61 | 41.7 | |
| PIDNet-LParam=37.08M, FLOPs=1653G, Input Resolution=4096 x 40962025.03 | 81.77 | 30.7 | 34.79 | |
| CGRSeg-LBackbone=EFv2-L, Param=35.64M, FLOPs=1536G, Input Resolution=4096 x 40962025.03 | 81.45 | 33.95 | 40.71 | |
| BiSeNetv2Param=3.35M, FLOPs=591G, Input Resolution=4096 x 40962025.03 | 72.92 | 24.48 | 31.71 |