Vision Language Navigation On Room2Room

spl

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
R2R+EnvDrop	0.61	Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout
RCM + SIL	0.59	Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
Tactical Rewind - short	0.41	Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation

0 of 3 row(s) selected.