{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bevbert-topo-metric-map-pre-training-for","title":"BEVBert: Multimodal Map Pre-training for Language-guided Navigation","arxiv_id":"2212.04385","date":"2022-12-08","proceeding":"ICCV 2023 1","authors":["Dong An","Yuankai Qi","Yangguang Li","Yan Huang","Liang Wang","Tieniu Tan","Jing Shao"],"abstract":"Large-scale pre-training has shown promising results on the vision-and-language navigation (VLN) task. However, most existing pre-training methods employ discrete panoramas to learn visual-textual associations. This requires the model to implicitly correlate incomplete, duplicate observations within the panoramas, which may impair an agent's spatial understanding. Thus, we propose a new map-based pre-training paradigm that is spatial-aware for use in VLN. Concretely, we build a local metric map to explicitly aggregate incomplete observations and remove duplicates, while modeling navigation dependency in a global topological map. This hybrid design can balance the demand of VLN for both short-term reasoning and long-term planning. Then, based on the hybrid map, we devise a pre-training framework to learn a multimodal map representation, which enhances spatial-aware cross-modal reasoning thereby facilitating the language-guided navigation goal. Extensive experiments demonstrate the effectiveness of the map-based pre-training route for VLN, and the proposed method achieves state-of-the-art on four VLN benchmarks.","url_abs":"https://arxiv.org/abs/2212.04385v2","url_pdf":"https://arxiv.org/pdf/2212.04385v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bevbert-topo-metric-map-pre-training-for","repo_url":"https://github.com/marsaki/vln-bevbert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"vision-and-language-navigation","task_name":"Vision and Language Navigation"},{"task_slug":"visual-navigation","task_name":"Visual Navigation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-navigation-on-room-to-room-1","task":"Visual Navigation","dataset":"R2R","model":"BEV-BERT","rank_in_archive_order":3,"of":11,"metrics":{"spl":"0.60"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.04385","atlas_url":"https://app.syntology.ai/?focus=2212.04385","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}