FOAM: A Follower-aware Speaker Model For Vision-and-Language Navigation
This addresses a specific bottleneck in vision-and-language navigation for AI agents, though it appears incremental relative to existing speaker-follower frameworks.
The paper tackles the problem of suboptimal instruction generation in vision-and-language navigation by proposing FOAM, a follower-aware speaker model that updates based on follower feedback to produce more suitable instructions. Experimental results show it outperforms strong baselines on Room-to-Room and Room-across-Room datasets.
The speaker-follower models have proven to be effective in vision-and-language navigation, where a speaker model is used to synthesize new instructions to augment the training data for a follower navigation model. However, in many of the previous methods, the generated instructions are not directly trained to optimize the performance of the follower. In this paper, we present \textsc{foam}, a \textsc{Fo}llower-\textsc{a}ware speaker \textsc{M}odel that is constantly updated given the follower feedback, so that the generated instructions can be more suitable to the current learning state of the follower. Specifically, we optimize the speaker using a bi-level optimization framework and obtain its training signals by evaluating the follower on labeled data. Experimental results on the Room-to-Room and Room-across-Room datasets demonstrate that our methods can outperform strong baseline models across settings. Analyses also reveal that our generated instructions are of higher quality than the baselines.