Multi-View Learning for Vision-and-Language Navigation

03/02/2020
by   Qiaolin Xia, et al.
7

Learning to navigate in a visual environment following natural language instructions is a challenging task because natural language instructions are highly variable, ambiguous, and under-specified. In this paper, we present a novel training paradigm, Learn from EveryOne (LEO), which leverages multiple instructions (as different views) for the same trajectory to resolve language ambiguity and improve generalization. By sharing parameters across instructions, our approach learns more effectively from limited training data and generalizes better in unseen environments. On the recent Room-to-Room (R2R) benchmark dataset, LEO achieves 16 as the base agent (25.3 Length (SPL). Further, LEO is complementary to most existing models for vision-and-language navigation, allowing for easy integration with the existing techniques, leading to LEO+, which creates the new state of the art, pushing the R2R benchmark to 62

READ FULL TEXT

page 2

page 8

page 13

page 14

page 15

page 16

02/25/2020

Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training

Learning to navigate in a visual environment following natural-language ...
03/29/2022

EnvEdit: Environment Editing for Vision-and-Language Navigation

In Vision-and-Language Navigation (VLN), an agent needs to navigate thro...
08/20/2021

Airbert: In-domain Pretraining for Vision-and-Language Navigation

Vision-and-language navigation (VLN) aims to enable embodied agents to n...
03/31/2020

Take the Scenic Route: Improving Generalization in Vision-and-Language Navigation

In the Vision-and-Language Navigation (VLN) task, an agent with egocentr...
04/18/2021

Natural Instructions: Benchmarking Generalization to New Tasks from Natural Language Instructions

Can we enable NLP models to appropriately respond to instructional promp...
06/02/2019

Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) requires grounding instructions, su...
06/09/2022

FOAM: A Follower-aware Speaker Model For Vision-and-Language Navigation

The speaker-follower models have proven to be effective in vision-and-la...