Semantic Segmentation on Cityscapes val
Metric: FPS (higher is better)
Metric: FPS (higher is better)
| # | Model↕ | FPS▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | DSNet(single-scale) | 81.9 | No | DSNet: A Novel Way to Use Atrous Convolutions in... | 2024-06-06 | Code |
| 2 | EoMT (DINOv2-L, single-scale, 1024x1024) | 25 | No | Your ViT is Secretly an Image Segmentation Model | 2025-03-24 | Code |
| 3 | StreamDEQ (1 iterations) | 4.3 | No | Representation Recycling for Streaming Video Ana... | 2022-04-28 | Code |
| 4 | StreamDEQ (2 iterations) | 2.9 | No | Representation Recycling for Streaming Video Ana... | 2022-04-28 | Code |
| 5 | StreamDEQ (4 iterations) | 1.9 | No | Representation Recycling for Streaming Video Ana... | 2022-04-28 | Code |
| 6 | StreamDEQ (8 iterations) | 1.1 | No | Representation Recycling for Streaming Video Ana... | 2022-04-28 | Code |