Semantic Segmentation On Trans10K
Métriques
GFLOPs
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | GFLOPs |
|---|---|
| u-net-convolutional-networks-for-biomedical | 124.55 |
| pyramid-scene-parsing-network | 187.03 |
| icnet-for-real-time-semantic-segmentation-on | 10.64 |
| encoder-decoder-with-atrous-separable | 37.98 |
| ocnet-object-context-network-for-scene | 43.31 |
| dual-attention-network-for-scene-segmentation | 198.00 |
| trans4trans-efficient-transformer-for | 34.38 |
| bisenet-bilateral-segmentation-network-for | 19.91 |
| segmenting-transparent-objects-in-the-wild | 61.31 |
| denseaspp-for-semantic-segmentation-in-street | 36.20 |
| segmenting-transparent-object-in-the-wild | 49.03 |
| fully-convolutional-networks-for-semantic-1 | 42.23 |
| refinenet-multi-path-refinement-networks-for | 44.56 |
| trans4trans-efficient-transformer-for | 10.45 |
| trans4trans-efficient-transformer-for | 19.92 |