DELAN: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive Learning

Mengfei Du, Binhao Wu, Jiwen Zhang, Zhihao Fan, Zejun Li, Ruipu Luo, Xuanjing Huang, Zhongyu Wei


Abstract
Vision-and-Language navigation (VLN) requires an agent to navigate in unseen environment by following natural language instruction. For task completion, the agent needs to align and integrate various navigation modalities, including instruction, observation and navigation history. Existing works primarily concentrate on cross-modal attention at the fusion stage to achieve this objective. Nevertheless, modality features generated by disparate uni-encoders reside in their own spaces, leading to a decline in the quality of cross-modal fusion and decision. To address this problem, we propose a Dual-levEL AligNment (DELAN) framework by cross-modal contrastive learning. This framework is designed to align various navigation-related modalities before fusion, thereby enhancing cross-modal interaction and action decision-making. Specifically, we divide the pre-fusion alignment into dual levels: instruction-history level and landmark-observation level according to their semantic correlations. We also reconstruct a dual-level instruction for adaptation to the dual-level alignment. As the training signals for pre-fusion alignment are extremely limited, self-supervised contrastive learning strategies are employed to enforce the matching between different modalities. Our approach seamlessly integrates with the majority of existing models, resulting in improved navigation performance on various VLN benchmarks, including R2R, R4R, RxR and CVDN.
Anthology ID:
2024.lrec-main.411
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
4605–4616
Language:
URL:
https://aclanthology.org/2024.lrec-main.411
DOI:
Bibkey:
Cite (ACL):
Mengfei Du, Binhao Wu, Jiwen Zhang, Zhihao Fan, Zejun Li, Ruipu Luo, Xuanjing Huang, and Zhongyu Wei. 2024. DELAN: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive Learning. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4605–4616, Torino, Italia. ELRA and ICCL.
Cite (Informal):
DELAN: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive Learning (Du et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.lrec-main.411.pdf