Vision-and-Language Navigation on Touchdown unseen (dev)
1.3SDTWGA
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GA2022.03 | 1.3 | 31 | |
| RConcat2022.03 | 1.8 | 29.6 | |
| VLN Transformer2022.03 | 1.9 | 29.5 | |
| ORAR full modelBackbone=ResNet 4th-to-last, Ablation=no junction type2022.03 | 4 | 26.6 | |
| ORAR full modelBackbone=ResNet pre-final2022.03 | 8.6 | 26.7 | |
| ORAR full modelBackbone=ResNet 4th-to-last, Ablation=no heading delta2022.03 | 14 | 20.5 | |
| ORAR full modelBackbone=ResNet 4th-to-last2022.03 | 14.3 | 20 |