SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation

Natural language instructions for visual navigation often use scene descriptions (e.g., 'bedroom') and object references (e.g., 'green chairs') to provide a breadcrumb trail to a goal location. This work presents a transformer-based vision-andlanguage navigation (VLN) agent that uses two different visual encoders -a scene classification network and an object detector -which produce features that match these two distinct types of visual cues. In our method, scene features contribute high-level contextual information that supports object-level processing. With this design, our model is able to use vision-and-language pretraining (i.e., learning the alignment between images and text from large-scale web data) to substantially improve performance on the Room-to-Room (R2R) [1] and Room-Across-Room (RxR) [2] benchmarks. Specifically, our approach leads to improvements of 1.8% absolute in SPL on R2R and 3.7% absolute in SR on RxR. Our analysis reveals even larger gains for navigation instructions that contain six or more object references, which further suggests that our approach is better able to use object features and align them to references in the instructions.