Does VLN Pretraining Work with Nonsensical or Irrelevant Instructions?

CoRR(2023)

引用 0|浏览4
暂无评分
摘要
Data augmentation via back-translation is common when pretraining Vision-and-Language Navigation (VLN) models, even though the generated instructions are noisy. But: does that noise matter? We find that nonsensical or irrelevant language instructions during pretraining can have little effect on downstream performance for both HAMT and VLN-BERT on R2R, and is still better than only using clean, human data. To underscore these results, we concoct an efficient augmentation method, Unigram + Object, which generates nonsensical instructions that nonetheless improve downstream performance. Our findings suggest that what matters for VLN R2R pretraining is the quantity of visual trajectories, not the quality of instructions.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络