{"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/multi-task-learning-for-segmentation-of","title":"Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks","arxiv_id":"1709.05932","date":"2017-09-18","proceeding":null,"authors":["Benjamin Bischke","Patrick Helber","Joachim Folz","Damian Borth","Andreas Dengel"],"abstract":"The increased availability of high resolution satellite imagery allows to\nsense very detailed structures on the surface of our planet. Access to such\ninformation opens up new directions in the analysis of remote sensing imagery.\nHowever, at the same time this raises a set of new challenges for existing\npixel-based prediction methods, such as semantic segmentation approaches. While\ndeep neural networks have achieved significant advances in the semantic\nsegmentation of high resolution images in the past, most of the existing\napproaches tend to produce predictions with poor boundaries. In this paper, we\naddress the problem of preserving semantic segmentation boundaries in high\nresolution satellite imagery by introducing a new cascaded multi-task loss. We\nevaluate our approach on Inria Aerial Image Labeling Dataset which contains\nlarge-scale and high resolution images. Our results show that we are able to\noutperform state-of-the-art methods by 8.3\\% without any additional\npost-processing step.","url_abs":"http://arxiv.org/abs/1709.05932v1","url_pdf":"http://arxiv.org/pdf/1709.05932v1.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":"multi-task-learning-for-segmentation-of","repo_url":"https://github.com/melissande/dhi-segmentation-buildings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.05932","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}