MODELS.md
April 30, 2022 ยท View on GitHub
Scene Parsing
Accurate Models
| Method | Backbone | ADE20K (mIoU) | Cityscapes (mIoU) | COCO-Stuff (mIoU) | Params (M) | GFLOPs (512x512) | GFLOPs (1024x1024) | Weights |
|---|---|---|---|---|---|---|---|---|
| SegFormer | MiT-B1 | 42.2 | 78.5 | 40.2 | 14 | 16 | 244 | ade |
| MiT-B2 | 46.5 | 81.0 | 44.6 | 28 | 62 | 717 | ade | |
| MiT-B3 | 49.4 | 81.7 | 45.5 | 47 | 79 | 963 | ade | |
| Light-Ham | VAN-S | 45.7 | - | - | 15 | 21 | - | - |
| VAN-B | 49.6 | - | - | 27 | 34 | - | - | |
| VAN-L | 51.0 | - | - | 46 | 55 | - | - | |
| Lawin | MiT-B1 | 42.1 | 79.0 | 40.5 | 14 | 13 | 218 | - |
| MiT-B2 | 47.8 | 81.7 | 45.2 | 30 | 45 | 563 | - | |
| MiT-B3 | 50.3 | 82.5 | 46.6 | 50 | 62 | 809 | - | |
| TopFormer | TopFormer-T | 34.6 | - | - | 1.4 | 0.6 | - | - |
| TopFormer-S | 37.0 | - | - | 3.1 | 1.2 | - | - | |
| TopFormer-B | 39.2 | - | - | 5.1 | 1.8 | - | - |
- mIoU results are with a single scale from official papers.
- ADE20K image size = 512x512
- Cityscapes image size = 1024x1024
- COCO-Stuff image size = 512x512
Real-time Models
| Method | Backbone | CityScapes-val (mIoU) | CamVid (mIoU) | Params (M) | GFLOPs (1024x2048) | Weights |
|---|---|---|---|---|---|---|
| BiSeNetv1 | ResNet-18 | 74.8 | 68.7 | 14 | 49 | - |
| BiSeNetv2 | - | 73.4 | 72.4 | 18 | 21 | - |
| SFNet | ResNetD-18 | 79.0 | - | 13 | - | - |
| DDRNet | DDRNet-23slim | 77.8 | 74.7 | 6 | 36 | city |
- mIoU results are with a single scale from official papers.
- Cityscapes image size = 1024x2048 (except BiSeNetv1 & 2 which uses 512x1024)
- CamVid image size = 960x720
Face Parsing
| Method | Backbone | HELEN-val (mIoU) | Params (M) | GFLOPs (512x512) | FPS (GTX1660ti) | Weights |
|---|---|---|---|---|---|---|
| BiSeNetv1 | ResNet-18 | 58.50 | 14 | 13 | 263 | HELEN |
| BiSeNetv2 | - | 58.58 | 18 | 15 | 195 | HELEN |
| DDRNet | DDRNet-23slim | 61.11 | 6 | 5 | 180 | HELEN |
| SFNet | ResNetD-18 | 61.00 | 14 | 31 | 56 | HELEN |