Transferable Representation Learning in Vision-and-Language Navigation
arXiv:1908.03409
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.
To appear in ICCV 2019
References in corpus (9)
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Representation Learning with Contrastive Predictive Coding
- VQA: Visual Question Answering
- On Evaluation of Embodied Navigation Agents
- Matterport3D: Learning from RGB-D Data in Indoor Environments
- Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
- End-to-End Retrieval in Continuous Space
- Learning Transferable Policies for Monocular Reactive MAV Control
- Multi-modal Discriminative Model for Vision-and-Language Navigation