{"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/esfnet-efficient-network-for-building","title":"ESFNet: Efficient Network for Building Extraction from High-Resolution Aerial Images","arxiv_id":"1903.12337","date":"2019-03-29","proceeding":null,"authors":["Jingbo Lin","Wei-Peng Jing","Houbing Song","Guang-Sheng Chen"],"abstract":"Building footprint extraction from high-resolution aerial images is always an\nessential part of urban dynamic monitoring, planning and management. It has\nalso been a challenging task in remote sensing research. In recent years, deep\nneural networks have made great achievement in improving accuracy of building\nextraction from remote sensing imagery. However, most of existing approaches\nusually require large amount of parameters and floating point operations for\nhigh accuracy, it leads to high memory consumption and low inference speed\nwhich are harmful to research. In this paper, we proposed a novel efficient\nnetwork named ESFNet which employs separable factorized residual block and\nutilizes the dilated convolutions, aiming to preserve slight accuracy loss with\nlow computational cost and memory consumption. Our ESFNet obtains a better\ntrade-off between accuracy and efficiency, it can run at over 100 FPS on single\nTesla V100, requires 6x fewer FLOPs and has 18x fewer parameters than\nstate-of-the-art real-time architecture ERFNet while preserving similar\naccuracy without any additional context module, post-processing and pre-trained\nscheme. We evaluated our networks on WHU Building Dataset and compared it with\nother state-of-the-art architectures. The result and comprehensive analysis\nshow that our networks are benefit for efficient remote sensing researches, and\nthe idea can be further extended to other areas. The code is public available\nat: https://github.com/mrluin/ESFNet-Pytorch","url_abs":"http://arxiv.org/abs/1903.12337v2","url_pdf":"http://arxiv.org/pdf/1903.12337v2.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":"esfnet-efficient-network-for-building","repo_url":"https://github.com/mrluin/ESFNet-Pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"management","task_name":"Management"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}