Video Semantic Segmentation On Cityscapes Val
Metriken
mIoU
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | mIoU | Paper Title | Repository |
|---|---|---|---|
| DeltaDist-DDRNet-39 | 79.9 | Delta Distillation for Efficient Video Processing | |
| LVS [12] | 76.8 | Low-Latency Video Semantic Segmentation | - |
| DFF [22] | 69.2 | Deep Feature Flow for Video Recognition | |
| FCN-50 [14] | 70.1 | Fully Convolutional Networks for Semantic Segmentation | |
| PSPNet-101 [20] | 79.7 | Pyramid Scene Parsing Network | |
| PSPNet-50 [20] | 78.1 | Pyramid Scene Parsing Network | |
| TMANet-50 | 80.3 | Temporal Memory Attention for Video Semantic Segmentation | |
| GRFP [15] | 73.6 | Semantic Video Segmentation by Gated Recurrent Flow Propagation | - |
| TDNet-50 [9] | 79.9 | Temporally Distributed Networks for Fast Video Semantic Segmentation |
0 of 9 row(s) selected.