Semantic Segmentation On Camvid
評価指標
Mean IoU
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | Mean IoU |
|---|---|
| rtformer-efficient-design-for-real-time | 82.5 |
| efficient-dense-modules-of-asymmetric | 66.4 |
| dense-decoder-shortcut-connections-for-single | 70.9 |
| efficient-road-lane-marking-detection-with | 63.5 |
| dsnet-a-novel-way-to-use-atrous-convolutions | 83.32 |
| efficient-semantic-video-segmentation-with | 76.3 |
| template-based-automatic-search-of-compact | 63.2% |
| improving-semantic-segmentation-via-video | 81.7% |
| deep-dual-resolution-networks-for-real-time | 80.6% |
| semantic-image-segmentation-with-deep | 61.6% |
| pidnet-a-real-time-semantic-segmentation | 82.0% |
| deep-spatio-temporal-random-fields-for | 75.2 |
| template-based-automatic-search-of-compact | 63.9% |
| segnet-a-deep-convolutional-encoder-decoder | 46.4% |
| dfanet-deep-feature-aggregation-for-real-time | 64.7% |
| multi-scale-context-aggregation-by-dilated | 65.3% |
| the-devil-is-in-the-labels-semantic | 83.7 |
| sernet-former-semantic-segmentation-by | 84.62 |
| the-one-hundred-layers-tiramisu-fully | 66.9% |
| bisenet-bilateral-segmentation-network-for | 68.7% |
| reseg-a-recurrent-neural-network-based-model | 58.8% |