Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration

Xiwen Liang, Fengda Zhu, Li Lingling, Hang Xu, Xiaodan Liang


Abstract
Vision-language navigation (VLN) is a challenging task due to its large searching space in the environment. To address this problem, previous works have proposed some methods of fine-tuning a large model that pretrained on large-scale datasets. However, the conventional fine-tuning methods require extra human-labeled navigation data and lack self-exploration capabilities in environments, which hinders their generalization of unseen scenes. To improve the ability of fast cross-domain adaptation, we propose Prompt-based Environmental Self-exploration (ProbES), which can self-explore the environments by sampling trajectories and automatically generates structured instructions via a large-scale cross-modal pretrained model (CLIP). Our method fully utilizes the knowledge learned from CLIP to build an in-domain dataset by self-exploration without human labeling. Unlike the conventional approach of fine-tuning, we introduce prompt tuning to achieve fast adaptation for language embeddings, which substantially improves the learning efficiency by leveraging prior knowledge. By automatically synthesizing trajectory-instruction pairs in any environment without human supervision and instruction prompt tuning, our model can adapt to diverse vision-language navigation tasks, including VLN and REVERIE. Both qualitative and quantitative results show that our ProbES significantly improves the generalization ability of the navigation model.
Anthology ID:
2022.acl-long.332
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4837–4851
Language:
URL:
https://aclanthology.org/2022.acl-long.332
DOI:
10.18653/v1/2022.acl-long.332
Bibkey:
Cite (ACL):
Xiwen Liang, Fengda Zhu, Li Lingling, Hang Xu, and Xiaodan Liang. 2022. Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4837–4851, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration (Liang et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2022.acl-long.332.pdf
Code
 liangcici/probes-vln
Data
Conceptual CaptionsObjects365Places