{"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/beyond-rgb-very-high-resolution-urban-remote","title":"Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks","arxiv_id":"1711.08681","date":"2017-11-23","proceeding":null,"authors":["Nicolas Audebert","Bertrand Le Saux","Sébastien Lefèvre"],"abstract":"In this work, we investigate various methods to deal with semantic labeling\nof very high resolution multi-modal remote sensing data. Especially, we study\nhow deep fully convolutional networks can be adapted to deal with multi-modal\nand multi-scale remote sensing data for semantic labeling. Our contributions\nare threefold: a) we present an efficient multi-scale approach to leverage both\na large spatial context and the high resolution data, b) we investigate early\nand late fusion of Lidar and multispectral data, c) we validate our methods on\ntwo public datasets with state-of-the-art results. Our results indicate that\nlate fusion make it possible to recover errors steaming from ambiguous data,\nwhile early fusion allows for better joint-feature learning but at the cost of\nhigher sensitivity to missing data.","url_abs":"http://arxiv.org/abs/1711.08681v1","url_pdf":"http://arxiv.org/pdf/1711.08681v1.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":"beyond-rgb-very-high-resolution-urban-remote","repo_url":"https://github.com/nshaud/DeepNetsForEO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-potsdam","task":"Semantic Segmentation","dataset":"Potsdam","model":"V-FuseNet","rank_in_archive_order":7,"of":11,"metrics":{"mIoU":"84.36"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-us3d","task":"Semantic Segmentation","dataset":"US3D","model":"vFuseNet","rank_in_archive_order":5,"of":11,"metrics":{"mIoU":"83.53"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-vaihingen","task":"Semantic Segmentation","dataset":"Vaihingen","model":"V-FuseNet","rank_in_archive_order":4,"of":13,"metrics":{"mIoU":"79.56"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1711.08681","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}