{"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/geosam-fine-tuning-sam-with-sparse-and-dense","title":"GeoSAM: Fine-tuning SAM with Multi-Modal Prompts for Mobility Infrastructure Segmentation","arxiv_id":"2311.11319","date":"2023-11-19","proceeding":null,"authors":["Rafi Ibn Sultan","Chengyin Li","Hui Zhu","Prashant Khanduri","Marco Brocanelli","Dongxiao Zhu"],"abstract":"In geographical image segmentation, performance is often constrained by the limited availability of training data and a lack of generalizability, particularly for segmenting mobility infrastructure such as roads, sidewalks, and crosswalks. Vision foundation models like the Segment Anything Model (SAM), pre-trained on millions of natural images, have demonstrated impressive zero-shot segmentation performance, providing a potential solution. However, SAM struggles with geographical images, such as aerial and satellite imagery, due to its training being confined to natural images and the narrow features and textures of these objects blending into their surroundings. To address these challenges, we propose Geographical SAM (GeoSAM), a SAM-based framework that fine-tunes SAM with automatically generated multi-modal prompts, combining point prompts from a pre-trained task-specific model as primary visual guidance and text prompts from a large language model as secondary semantic guidance to enhance model comprehension. GeoSAM outperforms existing approaches for mobility infrastructure segmentation in both familiar and completely unseen regions by at least 5\\% in mIoU, representing a significant leap in leveraging foundation models to segment mobility infrastructure, including both road and pedestrian infrastructure in geographical images. The source code can be found in this GitHub Repository: https://github.com/rafiibnsultan/GeoSAM.","url_abs":"https://arxiv.org/abs/2311.11319v3","url_pdf":"https://arxiv.org/pdf/2311.11319v3.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":"geosam-fine-tuning-sam-with-sparse-and-dense","repo_url":"https://github.com/rafiibnsultan/geosam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"visual-prompting","task_name":"Visual Prompting"},{"task_slug":"zero-shot-segmentation","task_name":"Zero Shot Segmentation"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[{"method_slug":"sam","method_name":"SAM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}