{"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/feature-pyramid-network-for-multi-class-land","title":"Feature Pyramid Network for Multi-Class Land Segmentation","arxiv_id":"1806.03510","date":"2018-06-09","proceeding":null,"authors":["Selim S. Seferbekov","Vladimir I. Iglovikov","Alexander V. Buslaev","Alexey A. Shvets"],"abstract":"Semantic segmentation is in-demand in satellite imagery processing. Because\nof the complex environment, automatic categorization and segmentation of land\ncover is a challenging problem. Solving it can help to overcome many obstacles\nin urban planning, environmental engineering or natural landscape monitoring.\nIn this paper, we propose an approach for automatic multi-class land\nsegmentation based on a fully convolutional neural network of feature pyramid\nnetwork (FPN) family. This network is consisted of pre-trained on ImageNet\nResnet50 encoder and neatly developed decoder. Based on validation results,\nleaderboard score and our own experience this network shows reliable results\nfor the DEEPGLOBE - CVPR 2018 land cover classification sub-challenge.\nMoreover, this network moderately uses memory that allows using GTX 1080 or\n1080 TI video cards to perform whole training and makes pretty fast\npredictions.","url_abs":"http://arxiv.org/abs/1806.03510v2","url_pdf":"http://arxiv.org/pdf/1806.03510v2.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":"feature-pyramid-network-for-multi-class-land","repo_url":"https://github.com/oikosohn/compound-loss-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"land-cover-classification","task_name":"Land Cover Classification"},{"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=1806.03510","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}