{"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/an-efficient-solution-for-semantic","title":"An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions","arxiv_id":"1902.07476","date":"2019-02-20","proceeding":null,"authors":["Sercan Türkmen","Janne Heikkilä"],"abstract":"Assigning a label to each pixel in an image, namely semantic segmentation,\nhas been an important task in computer vision, and has applications in\nautonomous driving, robotic navigation, localization, and scene understanding.\nFully convolutional neural networks have proved to be a successful solution for\nthe task over the years but most of the work being done focuses primarily on\naccuracy. In this paper, we present a computationally efficient approach to\nsemantic segmentation, while achieving a high mean intersection over union\n(mIOU), 70.33% on Cityscapes challenge. The network proposed is capable of\nrunning real-time on mobile devices. In addition, we make our code and model\nweights publicly available.","url_abs":"http://arxiv.org/abs/1902.07476v2","url_pdf":"http://arxiv.org/pdf/1902.07476v2.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":"an-efficient-solution-for-semantic","repo_url":"https://github.com/sercant/mobile-segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"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=1902.07476","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}