{"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/contextnet-exploring-context-and-detail-for","title":"ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time","arxiv_id":"1805.04554","date":"2018-05-11","proceeding":null,"authors":["Rudra P. K. Poudel","Ujwal Bonde","Stephan Liwicki","Christopher Zach"],"abstract":"Modern deep learning architectures produce highly accurate results on many\nchallenging semantic segmentation datasets. State-of-the-art methods are,\nhowever, not directly transferable to real-time applications or embedded\ndevices, since naive adaptation of such systems to reduce computational cost\n(speed, memory and energy) causes a significant drop in accuracy. We propose\nContextNet, a new deep neural network architecture which builds on factorized\nconvolution, network compression and pyramid representation to produce\ncompetitive semantic segmentation in real-time with low memory requirement.\nContextNet combines a deep network branch at low resolution that captures\nglobal context information efficiently with a shallow branch that focuses on\nhigh-resolution segmentation details. We analyse our network in a thorough\nablation study and present results on the Cityscapes dataset, achieving 66.1%\naccuracy at 18.3 frames per second at full (1024x2048) resolution (41.9 fps\nwith pipelined computations for streamed data).","url_abs":"http://arxiv.org/abs/1805.04554v4","url_pdf":"http://arxiv.org/pdf/1805.04554v4.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":"contextnet-exploring-context-and-detail-for","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"contextnet-exploring-context-and-detail-for","repo_url":"https://github.com/zh320/realtime-semantic-segmentation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"ContextNet","rank_in_archive_order":92,"of":99,"metrics":{"mIoU":"65.9%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.04554","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}