Take the scenic route: Improving generalization in vision-and-language navigation

Felix Yu, Zhiwei Deng, Karthik Narasimhan, Olga Russakovsky

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In the Vision-and-Language Navigation (VLN) task, an agent with egocentric vision navigates to a destination given natural language instructions. The act of manually annotating these instructions is timely and expensive, such that many existing approaches automatically generate additional samples to improve agent performance. However, these approaches still have difficulty generalizing their performance to new environments. In this work, we investigate the popular Room-to-Room (R2R) VLN benchmark and discover that what is important is not only the amount of data you synthesize, but also how you do it. We find that shortest path sampling, which is used by both the R2R benchmark and existing augmentation methods, encode biases in the action space of the agent which we dub as action priors. We then show that these action priors offer one explanation toward the poor generalization of existing works. To mitigate such priors, we propose a path sampling method based on random walks to augment the data. By training with this augmentation strategy, our agent is able to generalize better to unknown environments compared to the baseline, significantly improving model performance in the process.

Original languageEnglish (US)
Title of host publicationProceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
PublisherIEEE Computer Society
Pages4000-4004
Number of pages5
ISBN (Electronic)9781728193601
DOIs
StatePublished - Jun 2020
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020 - Virtual, Online, United States
Duration: Jun 14 2020Jun 19 2020

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2020-June
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

Conference2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
CountryUnited States
CityVirtual, Online
Period6/14/206/19/20

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Take the scenic route: Improving generalization in vision-and-language navigation'. Together they form a unique fingerprint.

  • Cite this

    Yu, F., Deng, Z., Narasimhan, K., & Russakovsky, O. (2020). Take the scenic route: Improving generalization in vision-and-language navigation. In Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020 (pp. 4000-4004). [9150847] (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2020-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW50498.2020.00468