Vision-Language Navigation with Random Environmental Mixup

TL;DR

This paper introduces Random Environmental Mixup (REM), a novel data augmentation technique for Vision-Language Navigation that creates cross-connected house scenes to improve agent generalization to unseen environments.

Contribution

The paper proposes REM, a new data augmentation method that explicitly reduces data bias across different house scenes in VLN tasks, enhancing generalization to unseen environments.

Findings

REM improves navigation performance in unseen scenes.

The approach reduces the performance gap between seen and unseen environments.

Our model achieves state-of-the-art results on VLN benchmarks.

Abstract

Vision-language Navigation (VLN) tasks require an agent to navigate step-by-step while perceiving the visual observations and comprehending a natural language instruction. Large data bias, which is caused by the disparity ratio between the small data scale and large navigation space, makes the VLN task challenging. Previous works have proposed various data augmentation methods to reduce data bias. However, these works do not explicitly reduce the data bias across different house scenes. Therefore, the agent would overfit to the seen scenes and achieve poor navigation performance in the unseen scenes. To tackle this problem, we propose the Random Environmental Mixup (REM) method, which generates cross-connected house scenes as augmented data via mixuping environment. Specifically, we first select key viewpoints according to the room connection graph for each scene. Then, we cross-connect the key views of different scenes to construct augmented scenes. Finally, we generate augmented instruction-path pairs in the cross-connected scenes. The experimental results on benchmark datasets demonstrate that our augmentation data via REM help the agent reduce its performance gap between the seen and unseen environment and improve the overall performance, making our model the best existing approach on the standard VLN benchmark. The code have released: https://github.com/LCFractal/VLNREM.