{"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/road-extraction-by-deep-residual-u-net","title":"Road Extraction by Deep Residual U-Net","arxiv_id":"1711.10684","date":"2017-11-29","proceeding":null,"authors":["Zhengxin Zhang","Qingjie Liu","Yunhong Wang"],"abstract":"Road extraction from aerial images has been a hot research topic in the field\nof remote sensing image analysis. In this letter, a semantic segmentation\nneural network which combines the strengths of residual learning and U-Net is\nproposed for road area extraction. The network is built with residual units and\nhas similar architecture to that of U-Net. The benefits of this model is\ntwo-fold: first, residual units ease training of deep networks. Second, the\nrich skip connections within the network could facilitate information\npropagation, allowing us to design networks with fewer parameters however\nbetter performance. We test our network on a public road dataset and compare it\nwith U-Net and other two state of the art deep learning based road extraction\nmethods. The proposed approach outperforms all the comparing methods, which\ndemonstrates its superiority over recently developed state of the arts.","url_abs":"http://arxiv.org/abs/1711.10684v1","url_pdf":"http://arxiv.org/pdf/1711.10684v1.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":"road-extraction-by-deep-residual-u-net","repo_url":"https://github.com/JifeiWang-WHU/Pytorch_Building_extraction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"road-extraction-by-deep-residual-u-net","repo_url":"https://github.com/Kaido0/Brain-Tissue-Segment-Keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"road-extraction-by-deep-residual-u-net","repo_url":"https://github.com/Lkruitwagen/remote-sensing-solar-pv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"road-extraction-by-deep-residual-u-net","repo_url":"https://github.com/edwinpalegre/EE8204-ResUNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"road-extraction-by-deep-residual-u-net","repo_url":"https://github.com/galprz/brain-tumor-segemntation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"road-extraction-by-deep-residual-u-net","repo_url":"https://github.com/galprz/brain-tumor-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"road-extraction-by-deep-residual-u-net","repo_url":"https://github.com/hemanth346/mde_bs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"road-extraction-by-deep-residual-u-net","repo_url":"https://github.com/janpalasek/resunet-tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"road-extraction-by-deep-residual-u-net","repo_url":"https://github.com/nikhilroxtomar/Deep-Residual-Unet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"road-extraction-by-deep-residual-u-net","repo_url":"https://github.com/nikhilroxtomar/semantic-segmentation-architecture","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"road-extraction-by-deep-residual-u-net","repo_url":"https://github.com/rishikksh20/ResUnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"road-extraction-by-deep-residual-u-net","repo_url":"https://github.com/satellitevu/satellitevu-aws-disaster-response-hackathon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"road-extraction-by-deep-residual-u-net","repo_url":"https://github.com/z0978916348/Localization_and_Segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"lesion-segmentation","task_name":"Lesion Segmentation"},{"task_slug":"lung-nodule-segmentation","task_name":"Lung Nodule Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"skin-cancer-segmentation","task_name":"Skin Cancer Segmentation"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/lesion-segmentation-on-anatomical-tracings-of","task":"Lesion Segmentation","dataset":"Anatomical Tracings of Lesions After Stroke (ATLAS)","model":"ResUNet","rank_in_archive_order":3,"of":4,"metrics":{"Dice":"0.4702","IoU":"0.3549","Precision":"0.5941","Recall":"0.4537"},"uses_additional_data":false},{"leaderboard":"/sota/lung-nodule-segmentation-on-luna","task":"Lung Nodule Segmentation","dataset":"LUNA","model":"Residual U-Net","rank_in_archive_order":2,"of":5,"metrics":{"AUC":"0.9849","F1 score":"0.9690"},"uses_additional_data":false},{"leaderboard":"/sota/retinal-vessel-segmentation-on-chase_db1","task":"Retinal Vessel Segmentation","dataset":"CHASE_DB1","model":"Residual U-Net","rank_in_archive_order":12,"of":16,"metrics":{"AUC":"0.9779","F1 score":"0.7800"},"uses_additional_data":false},{"leaderboard":"/sota/retinal-vessel-segmentation-on-drive","task":"Retinal Vessel Segmentation","dataset":"DRIVE","model":"Residual U-Net","rank_in_archive_order":14,"of":22,"metrics":{"AUC":"0.9779","F1 score":"0.8149"},"uses_additional_data":false},{"leaderboard":"/sota/retinal-vessel-segmentation-on-rose-1-dvc","task":"Retinal Vessel Segmentation","dataset":"ROSE-1 DVC","model":"ResU-Net","rank_in_archive_order":3,"of":5,"metrics":{"Dice Score":"65.67"},"uses_additional_data":false},{"leaderboard":"/sota/retinal-vessel-segmentation-on-rose-1-svc","task":"Retinal Vessel Segmentation","dataset":"ROSE-1 SVC","model":"ResU-Net","rank_in_archive_order":4,"of":5,"metrics":{"Dice Score":"74.61"},"uses_additional_data":false},{"leaderboard":"/sota/retinal-vessel-segmentation-on-rose-1-svc-dvc","task":"Retinal Vessel Segmentation","dataset":"ROSE-1 SVC-DVC","model":"ResU-Net","rank_in_archive_order":3,"of":5,"metrics":{"Dice Score":"74.61"},"uses_additional_data":false},{"leaderboard":"/sota/retinal-vessel-segmentation-on-rose-2","task":"Retinal Vessel Segmentation","dataset":"ROSE-2","model":"ResU-Net","rank_in_archive_order":4,"of":5,"metrics":{"Dice Score":"67.25"},"uses_additional_data":false},{"leaderboard":"/sota/retinal-vessel-segmentation-on-stare","task":"Retinal Vessel Segmentation","dataset":"STARE","model":"Residual U-Net","rank_in_archive_order":9,"of":10,"metrics":{"F1 score":"0.8388"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-bjroad","task":"Semantic Segmentation","dataset":"BJRoad","model":"Res-UNet","rank_in_archive_order":10,"of":11,"metrics":{"IoU":"54.24"},"uses_additional_data":false},{"leaderboard":"/sota/skin-cancer-segmentation-on-kaggle-skin","task":"Skin Cancer Segmentation","dataset":"Kaggle Skin Lesion Segmentation","model":"Residual U-Net","rank_in_archive_order":2,"of":3,"metrics":{"AUC":"0.9396","F1 score":"0.8799"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.10684","atlas_url":"https://app.syntology.ai/?focus=1711.10684","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}