Transferable Representation Learning in Vision-and-Language Navigation

TL;DR

This paper introduces a transfer learning approach that adapts pre-trained vision and language models to improve performance in vision-and-language navigation tasks by focusing on sequence alignment and coherence.

Contribution

It presents a novel method for domain-adapting pre-trained models to enhance VLN agent effectiveness through sequence alignment and coherence tasks.

Findings

Improved success rate weighted by path length (SPL) in R2R tasks.

Effective transfer of domain-adapted representations to VLN agents.

Abstract

Vision-and-Language Navigation (VLN) tasks such as Room-to-Room (R2R) require machine agents to interpret natural language instructions and learn to act in visually realistic environments to achieve navigation goals. The overall task requires competence in several perception problems: successful agents combine spatio-temporal, vision and language understanding to produce appropriate action sequences. Our approach adapts pre-trained vision and language representations to relevant in-domain tasks making them more effective for VLN. Specifically, the representations are adapted to solve both a cross-modal sequence alignment and sequence coherence task. In the sequence alignment task, the model determines whether an instruction corresponds to a sequence of visual frames. In the sequence coherence task, the model determines whether the perceptual sequences are predictive sequentially in the instruction-conditioned latent space. By transferring the domain-adapted representations, we improve competitive agents in R2R as measured by the success rate weighted by path length (SPL) metric.