{"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/maplm-a-real-world-large-scale-vision","title":"MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding","arxiv_id":null,"date":"2024-01-01","proceeding":"CVPR 2024 1","authors":["Xu Cao","Tong Zhou","Yunsheng Ma","Wenqian Ye","Can Cui","Kun Tang","Zhipeng Cao","Kaizhao Liang","Ziran Wang","James M. Rehg","Chao Zheng"],"abstract":"    Vision-language generative AI has demonstrated remarkable promise for empowering cross-modal scene understanding of autonomous driving and high-definition (HD) map systems. However current benchmark datasets lack multi-modal point cloud image and language data pairs. Recent approaches utilize visual instruction learning and cross-modal prompt engineering to expand vision-language models into this domain. In this paper we propose a new vision-language benchmark that can be used to finetune traffic and HD map domain-specific foundation models. Specifically we annotate and leverage large-scale broad-coverage traffic and map data extracted from huge HD map annotations and use CLIP and LLaMA-2 / Vicuna to finetune a baseline model with instruction-following data. Our experimental results across various algorithms reveal that while visual instruction-tuning large language models (LLMs) can effectively learn meaningful representations from MAPLM-QA there remains significant room for further advancements. To facilitate applying LLMs and multi-modal data into self-driving research we will release our visual-language QA data and the baseline models at GitHub.com/LLVM-AD/MAPLM.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2024/html/Cao_MAPLM_A_Real-World_Large-Scale_Vision-Language_Benchmark_for_Map_and_Traffic_CVPR_2024_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2024/papers/Cao_MAPLM_A_Real-World_Large-Scale_Vision-Language_Benchmark_for_Map_and_Traffic_CVPR_2024_paper.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":"maplm-a-real-world-large-scale-vision","repo_url":"https://github.com/llvm-ad/maplm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}