CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representations

TL;DR

This paper introduces CLEAR, a method that enhances vision-language navigation by developing cross-lingual, environment-agnostic representations, enabling better generalization across languages and unseen environments.

Contribution

The paper proposes a novel approach to learn shared cross-lingual and environment-agnostic visual representations for VLN tasks, improving generalization and transferability.

Findings

Significant performance improvements on Room-Across-Room dataset.

Effective transfer of learned representations to other VLN tasks.

Enhanced generalization to unseen environments and languages.

Abstract

Vision-and-Language Navigation (VLN) tasks require an agent to navigate through the environment based on language instructions. In this paper, we aim to solve two key challenges in this task: utilizing multilingual instructions for improved instruction-path grounding and navigating through new environments that are unseen during training. To address these challenges, we propose CLEAR: Cross-Lingual and Environment-Agnostic Representations. First, our agent learns a shared and visually-aligned cross-lingual language representation for the three languages (English, Hindi and Telugu) in the Room-Across-Room dataset. Our language representation learning is guided by text pairs that are aligned by visual information. Second, our agent learns an environment-agnostic visual representation by maximizing the similarity between semantically-aligned image pairs (with constraints on object-matching) from different environments. Our environment agnostic visual representation can mitigate the environment bias induced by low-level visual information. Empirically, on the Room-Across-Room dataset, we show that our multilingual agent gets large improvements in all metrics over the strong baseline model when generalizing to unseen environments with the cross-lingual language representation and the environment-agnostic visual representation. Furthermore, we show that our learned language and visual representations can be successfully transferred to the Room-to-Room and Cooperative Vision-and-Dialogue Navigation task, and present detailed qualitative and quantitative generalization and grounding analysis. Our code is available at https://github.com/jialuli-luka/CLEAR