Vision Language Navigation On Room2Room
평가 지표
spl
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | spl | Paper Title | Repository |
|---|---|---|---|
| Tactical Rewind - short | 0.41 | Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation | |
| RCM + SIL | 0.59 | Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation | - |
| R2R+EnvDrop | 0.61 | Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout |
0 of 3 row(s) selected.